[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDRNPSX6FNBQKAFW2W4KA5":3,"skill-same:01M7FDRNPSX6FNBQKAFW2W4KA5":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FDRNPSX6FNBQKAFW2W4KA5","kill-argument",null,"Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says \"kill argument\", \"adversarial review\", \"hostile review\", \"rebuttal preparation\", \"reviewer-2 simulation\", or before submitting a theory paper that has already passed standard review rounds.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fkill-argument\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: kill-argument\ndescription: \"Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says \\\"kill argument\\\", \\\"adversarial review\\\", \\\"hostile review\\\", \\\"rebuttal preparation\\\", \\\"reviewer-2 simulation\\\", or before submitting a theory paper that has already passed standard review rounds.\"\nargument-hint: \"[paper-directory]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, spawn_agent\n---\n\n# Kill Argument Exercise: Adversarial Attack-Defense Review\n\n> **Codex assurance:** both fresh agents are OpenAI-family, so the base JSON\n> records `review_independence: same-family` and\n> `acceptance_status: provisional`. The mechanical count mapping may drive the\n> next step, but it is not cross-family acceptance. Call failure emits ERROR.\n\nStress-test the headline claims of a paper against the strongest possible rejection argument: **$ARGUMENTS**\n\n## Why This Exists\n\nStandard score-based reviews (`\u002Fresearch-review`, `\u002Fauto-paper-improvement-loop`) tend to produce **balanced** weakness lists.  Each weakness gets ~equal attention, ranked CRITICAL > MAJOR > MINOR.  Empirically, this misses one specific failure mode: the **single most damaging argument** a reviewer would write in a rejection paragraph — the one sentence that, if a senior area chair reads it, kills the paper.\n\nA balanced reviewer might list \"scope-overclaim risk\" as MAJOR alongside 3-5 other MAJORs, never quite committing.  An adversarial reviewer **must commit**: their entire job is to convince the area chair to reject in 200 words.\n\nThis skill runs that adversarial pass deliberately, then forces a second fresh reviewer to defend point-by-point, classify each rejection as already-fixed \u002F partially-fixed \u002F still-unresolved, and surface what's actually load-bearing.\n\n**Empirical motivation:** in a real submission run, after several rounds of standard improvement (score 7-8\u002F10), the kill-argument exercise surfaced framing weaknesses that no prior review caught (e.g., a setting being mostly conditional rather than truly general, or a baseline being irrelevant to real systems).  Author rebuttal forced explicit scope qualifications in abstract and discussion that weren't visible from the score-based reviews alone.\n\n## How This Differs From Other Review Skills\n\n| Skill | What it asks the reviewer | Output |\n|-------|---------------------------|--------|\n| Standard peer review | \"Score this paper, list weaknesses by severity\" | balanced weakness list |\n| `\u002Fresearch-review` | \"Deep technical review of methods + claims\" | structured deep critique |\n| `\u002Fproof-checker` | \"Is this theorem actually proved?\" | per-step proof obligation audit |\n| `\u002Fpaper-claim-audit` | \"Does the paper report numbers truthfully?\" | per-claim evidence verification |\n| `\u002Fcitation-audit` | \"Are citations real and used in correct context?\" | per-entry KEEP\u002FFIX\u002FREPLACE\u002FREMOVE |\n| **`\u002Fkill-argument`** | **\"Write the single strongest rejection paragraph; then defend it.\"** | **attack memo + per-point defense + unresolved surfaced** |\n\nThis skill is **complementary**, not a replacement.  Run after standard reviews when you want to know what the worst-case reviewer paragraph would look like, before camera-ready or rebuttal preparation.\n\n## When To Use\n\n- After 1-2 rounds of `\u002Fauto-paper-improvement-loop` settled at a stable score, but before submission.  Surfaces what additional fixes would close the headline-attack gap.\n- During rebuttal preparation, to predict reviewer-2's strongest objection so you can prepare the response in advance.\n- For theory papers with a high-level title that may oversimplify the actual theorem (the most common reject-attack pattern).\n- For papers where a reviewer might attack scope, assumption-vs-claim mismatch, missing proof obligations, or evidence-vs-headline gaps.\n\nThis skill is most valuable for **theory papers** with ≥5 theorem-class environments (so the headline depends on real proof obligations).  For empirical papers without theorems, use `\u002Fresearch-review` instead.\n\n## Constants\n\n- **REVIEWER_MODEL** = `gpt-6-astra` (default; specify `gpt-5.4` if you want to fall back to the legacy default). Reviewer reasoning effort = `ultra` for the deep-audit core threads (capability fallback never below `xhigh`).\n- **CONTEXT_POLICY** = `fresh` (REVIEWER_BIAS_GUARD).  Each thread is a fresh `spawn_agent` call.  **Never** use `send_input`.  No prior review summary, fix list, or executor explanation enters either prompt.\n- **ATTACK_LENGTH** = approximately 200 words (do not exceed 250).  Single coherent argument, not a list.\n- **DEFENSE_DECOMPOSITION** = 3-7 atomic rejection points extracted from the attack memo.  Each gets its own classification.\n- **CLASSIFICATION** = `answered_by_current_text` \u002F `partially_answered` \u002F `still_unresolved`.  (Names chosen so the adjudicator does not assume \"fixed\" implies prior history of patching — they read the paper as a fresh reviewer would.)\n- **OUTPUT** = `KILL_ARGUMENT.md` (human-readable) + `KILL_ARGUMENT.json` (machine-readable) in the paper directory.\n- **RENDER_HTML = true** — When `true` (default), auto-render `KILL_ARGUMENT.md` to HTML after writing the report via `\u002Frender-html \"\u003Cpaper-dir>\u002FKILL_ARGUMENT.md\" --json \"\u003Cpaper-dir>\u002FKILL_ARGUMENT.json\"`. Uses **full review gate** (audit-class artifact). Set `false` to skip, or pass `— render html: false`. **Non-blocking**: failures don't invalidate the kill-argument verdict.\n\n## Workflow\n\nThe attack and adjudication calls are fresh, read-only Codex shards. They return\nstructured per-point records with stable `dedup_key` identifiers; neither call\nwrites the paper or emits cross-family acceptance. The parent computes the\ntop-level mapping mechanically and records a same-family provisional verdict.\nIf `spawn_agent` is unavailable, use fresh sequential contexts where supported;\notherwise emit `BLOCKED` rather than inventing a verdict. See\n[`fan-out-pattern.md`](..\u002Fshared-references\u002Ffan-out-pattern.md).\n\n### Step 1: Discover paper files\n\nLocate the paper directory and inventory the source.\n\n```bash\nPAPER_DIR=\"$ARGUMENTS\"   # e.g., paper-overleaf\u002F or paper\u002F\ncd \"$PAPER_DIR\"\n\n# Find the LaTeX entry point\nENTRY=$(grep -lE '^\\\\documentclass' *.tex 2>\u002Fdev\u002Fnull | head -1)\necho \"Entry: $ENTRY\"\n\n# Find all source files codex should read\nfind . -name \"*.tex\" -not -path \".\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull\nfind . -name \"*.bib\" -not -path \".\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull\nfind figures\u002F -name \"*.pdf\" -o -name \"*.png\" 2>\u002Fdev\u002Fnull\nls -la *.pdf 2>\u002Fdev\u002Fnull  # compiled PDF\n```\n\nIf a compiled PDF is missing, the skill should still run on .tex source alone, but the prompt should mention this so the reviewer doesn't waste cycles trying to extract from a non-existent PDF.\n\n### Step 2: Attack memo (Thread 1, fresh codex)\n\nInvoke `spawn_agent` (NOT `send_input`) with the following prompt structure. Use absolute or paper-directory-relative paths inside the prompt; do not rely on a `cwd` parameter.\n\n```\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: ultra\n  message: |\n    You are simulating a hostile NeurIPS \u002F ICLR \u002F ICML reviewer for a paper.\n    This is a kill-argument adversarial check — your task is NOT to give a\n    balanced review but to construct the **single strongest argument for\n    rejecting this paper**.\n\n    ## Files to read\n    - LaTeX entry: \u003CENTRY>\n    - All section files under sections\u002F or wherever they live\n    - Macro files (math_commands.tex, etc.)\n    - Compiled PDF: \u003Cmain.pdf> (if available)\n\n    Read the source carefully. Do not consult any prior reviews, fix lists,\n    or summaries; this must be a fresh, zero-context adversarial pass.\n\n    ## Your task\n    Construct the single best argument to reject this paper in approximately\n    200 words. Your goal is to write the worst-case rejection memo a senior\n    NeurIPS area chair would produce after reading the paper.\n\n    Focus on these axes (pick the most damaging combination, do not list all):\n    1. Theorem validity: are central theorems actually proved as stated?\n    2. Assumption-vs-claim mismatch: does the body silently retreat to a\n       narrower object than the title\u002Fabstract advertise?\n    3. Missing proof obligations: is a fundamental lemma invoked but not\n       proved (e.g., concentration, generic position, prefactor envelope)\n       that the headline depends on?\n    4. Limit-order ambiguity: are limits in K\u002Fn\u002Fd\u002Feps composed in a way the\n       paper does not commit to?\n    5. Claim-vs-evidence gap: is the empirical\u002Fnumerical evidence too narrow\n       to support the breadth of the stated theorem or take-away?\n    6. Scope overclaim: does the title or abstract sell a result substantially\n       broader than what the body proves?\n\n    ## Constraints\n    - Approximately 200 words total (do NOT exceed 250).\n    - Single argument, not a list — pick the most damaging line of attack\n      and develop it.\n    - Cite specific file:line locations or equation numbers when accusing.\n    - Tone: dispassionate but uncompromising. Do NOT hedge. Do NOT acknowledge\n      mitigations the paper might have made elsewhere. This is the rejection\n      paragraph; the defense gets the next pass.\n    - Do NOT reference prior review rounds, fix lists, or any context outside\n      the current paper files.\n\n    Output: just the rejection memo, nothing else.\n```\n\nSave the returned `agent_id` for the trace; do NOT pass it to Thread 2.  Save the attack memo verbatim — both Thread 2 and the human-readable report use it.\n\n### Step 3: Adjudication memo (Thread 2, fresh codex with attack + paper)\n\nInvoke a second `spawn_agent` call (still NOT `send_input` — Thread 2 is independent of Thread 1's Codex agent history):\n\n```\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: ultra\n  message: |\n    You are an independent area-chair adjudicator examining whether the\n    current paper text answers a hostile reviewer's rejection memo.\n    You are NOT the paper's defender — your job is to read the attack\n    point-by-point and rule, from the current source files alone,\n    whether each point stands or falls. Fresh, zero-context adjudication;\n    do not reference any prior reviews \u002F fix lists.\n\n    ## Paper files\n    [list paths same as Step 2]\n\n    ## The hostile reviewer's rejection memo (the \"attack\")\n    > \u003Cattack memo verbatim from Thread 1>\n\n    ## Your task\n    The attack is one continuous argument, but it makes multiple distinct\n    rejection points that you must adjudicate separately. Decompose the\n    attack into its atomic rejection points (3-7 of them), then for each\n    point classify it:\n\n    - answered_by_current_text: the current paper source already mitigates\n      this point (cite specific file:line evidence)\n    - partially_answered: paper has some response but not enough to refute\n      the attack as written\n    - still_unresolved: paper has no effective response\n\n    The label `answered_by_current_text` is intentional — \"fixed\" implies\n    history of patching and biases toward optimism. You are reading the\n    paper as a reviewer would, with no knowledge of prior round drafts.\n\n    For each rejection point, output:\n    ### Point P_n: \u003Cshort label>\n    **Attack claim**: \u003Cthe specific accusation, ~30 words>\n    **Verdict**: answered_by_current_text | partially_answered | still_unresolved\n    **Evidence (or lack of)**: \u003Ccite file:line, ~50 words>\n    **Severity if unresolved**: critical | major | minor\n    **If unresolved, recommended fix**: \u003Cone specific actionable sentence>\n\n    After per-point analysis, output:\n\n    ## Summary\n    Total rejection points: N\n    - answered_by_current_text: X\n    - partially_answered: Y\n    - still_unresolved: Z\n\n    ## Net assessment\n    \u003Cone short paragraph: would this paper survive a senior area-chair read\n    of the attack memo, given only what is in the current source? Be honest —\n    if Y or Z > 0 and they hit the headline, say so.>\n\n    ## Top action items (in priority order, max 3)\n    1. ...\n    2. ...\n    3. ...\n\n    ## Constraints\n    - Do NOT consult any prior round reviews or fix lists. Adjudication must\n      be made strictly from current paper files.\n    - If the paper cannot refute a point, do NOT minimize — keep severity\n      honest.\n    - If a point reflects an author-chosen position (e.g., conscious title\n      scope decision), classify as `partially_answered` with a note that the\n      position is intentional, AND say whether this position is sustainable\n      under the attack — do NOT auto-grade as `answered_by_current_text`\n      just because it is intentional.\n    - Be specific. No flattery, no hedging, no rationalizing on the paper's\n      behalf.\n```\n\nSave the returned `agent_id`.\n\n### Step 4: Write KILL_ARGUMENT.md and KILL_ARGUMENT.json\n\nCompose the human-readable report `\u003Cpaper-dir>\u002FKILL_ARGUMENT.md`:\n\n```markdown\n# Kill Argument Report — \u003Cpaper title>\n\n**Date**: \u003CYYYY-MM-DD>\n**Reviewer model**: gpt-6-astra ultra, fresh agents (no send_input)\n**Attack agent**: \u003Cagent_id 1>\n**Adjudicator agent**: \u003Cagent_id 2>\n**Verdict**: \u003CPASS \u002F WARN \u002F FAIL \u002F NOT_APPLICABLE \u002F BLOCKED \u002F ERROR> (`reason_code: \u003C...>`)\n\n## Net assessment\n\n\u003Cparagraph from adjudicator memo's \"Net assessment\">\n\n## Attack memo (verbatim)\n\n> \u003Cattack memo from Thread 1>\n\n## Adjudication (per-point)\n\n\u003Ccopy verbatim from Thread 2 — uses labels answered_by_current_text \u002F partially_answered \u002F still_unresolved>\n\n## Top action items\n\n\u003Ccopy from Thread 2>\n\n## Recommendation\n\nIf P_4 (or whatever still_unresolved critical) is research-level, record\nit as a known open problem in the conclusion \u002F limitations. If it is\nwriting-level, queue for next \u002Fauto-paper-improvement-loop round.\n```\n\nCompose the machine-readable `\u003Cpaper-dir>\u002FKILL_ARGUMENT.json` per the\nARIS Audit Artifact Schema (`shared-references\u002Fassurance-contract.md`):\n\n```json\n{\n  \"audit_skill\": \"kill-argument\",\n  \"verdict\": \"PASS | WARN | FAIL | NOT_APPLICABLE | BLOCKED | ERROR\",\n  \"reason_code\": \"\u003Csee verdict mapping below>\",\n  \"summary\": \"\u003Cone-line summary, ~80 chars>\",\n  \"audited_input_hashes\": {\n    \"main.tex\":                          \"sha256:\u003C...>\",\n    \"sec\u002F0.abstract.tex\":                \"sha256:\u003C...>\",\n    \"sec\u002F\u003Ceach-section>.tex\":            \"sha256:\u003C...>\",\n    \"references.bib\":                    \"sha256:\u003C...>\",\n    \"main.pdf\":                          \"sha256:\u003C...>\"\n  },\n  \"trace_path\": \".aris\u002Ftraces\u002Fkill-argument\u002F\u003Cdate>_run\u003CNN>\u002F\",\n  \"agent_id\": \"\u003Cdefense agent_id — primary; attack agent_id in details>\",\n  \"executor_model\": \"codex-gpt-6-astra\",\n  \"executor_family\": \"openai\",\n  \"reviewer_model\": \"gpt-6-astra\",\n  \"reviewer_family\": \"openai\",\n  \"review_independence\": \"same-family\",\n  \"acceptance_status\": \"provisional\",\n  \"reviewer_reasoning\": \"ultra\",\n  \"generated_at\": \"\u003CUTC ISO-8601>\",\n  \"details\": {\n    \"attack_agent_id\": \"\u003Cagent_id 1>\",\n    \"defense_agent_id\": \"\u003Cagent_id 2 — same as top-level agent_id>\",\n    \"attack_memo\": \"\u003Cverbatim>\",\n    \"decomposed_points\": [\n      {\n        \"id\": \"P_1\",\n        \"label\": \"\u003Cshort label>\",\n        \"attack_claim\": \"\u003C...>\",\n        \"verdict\": \"answered_by_current_text | partially_answered | still_unresolved\",\n        \"evidence\": \"\u003Cfile:line citation>\",\n        \"severity_if_unresolved\": \"critical | major | minor\",\n        \"recommended_fix\": \"\u003C...>\"\n      }\n    ],\n    \"counts\": {\n      \"answered_by_current_text\": \u003Cint>,\n      \"partially_answered\":       \u003Cint>,\n      \"still_unresolved\":         \u003Cint>\n    },\n    \"net_assessment\": \"\u003Cadjudicator memo's net assessment>\",\n    \"top_action_items\": [\"...\", \"...\", \"...\"]\n  }\n}\n```\n\n**Hash inputs** (`audited_input_hashes`): use paper-relative paths,\n`sha256` of every `.tex` consumed plus `references.bib` and the\ncompiled `main.pdf` if it exists. The verifier rehashes these on\n`verify_paper_audits.sh` and flags `STALE` if the user edited the\npaper after running the audit.\n\n**Verdict mapping** (every (counts, severity) tuple must hit exactly one row):\n\n| Verdict | reason_code | Trigger |\n|---|---|---|\n| `FAIL` | `unresolved_critical` | ≥1 `still_unresolved` at `critical` severity |\n| `WARN` | `unresolved_major_or_minor` | ≥1 `still_unresolved` at `major` or `minor` severity (and no `critical`) |\n| `WARN` | `partial_critical_or_repeated_major` | 0 `still_unresolved`, AND ≥1 `partially_answered` at `critical` or `major` |\n| `PASS` | `defense_survives_with_minor_partial_only` | 0 `still_unresolved`, AND ≥1 `partially_answered`, all at `minor` severity |\n| `PASS` | `defense_survives` | 0 `still_unresolved`, AND 0 `partially_answered` |\n| `NOT_APPLICABLE` | `not_theory_or_scope_paper` | Paper has \u003C2 `\\begin{theorem\\|lemma\\|proposition\\|corollary}` AND no scope \u002F generality claims in abstract |\n| `NOT_APPLICABLE` | `headline_unstable` | Title or abstract changed within the last 2 commits — re-run after headline stabilizes |\n| `BLOCKED` | `paper_compile_failed` | Compiled PDF missing AND `main.tex` does not compile clean — adjudication needs source fidelity |\n| `BLOCKED` | `source_files_missing` | `main.tex` not found, or no `sec\u002F*.tex` files |\n| `ERROR` | `codex_api_error` | `spawn_agent` call failed |\n| `ERROR` | `decomposition_parse_failed` | Adjudicator thread did not return parseable per-point structure |\n| `ERROR` | `trace_save_failed` | Trace directory write failed |\n\n`PASS` requires `still_unresolved == 0`. With `still_unresolved == 0`, any\n`partially_answered` at `major` or higher makes the best available verdict\n`WARN` — never `PASS`.\n\nThe verdict is computed from the per-point counts; do NOT let the\ndefense thread output the top-level verdict directly (that would let\nit self-grade). The skill code does the verdict mapping.\n\n### Step 5: Print summary\n\nTo the user:\n\n```\n🗡  Kill Argument complete.\n\n  Attack: \u003Cone-sentence summary of the rejection thrust>\n\n  Adjudication breakdown:\n    answered_by_current_text:   X\n    partially_answered:         Y\n    still_unresolved:           Z   ← critical: \u003Cnames>\n\n  Verdict: \u003CPASS \u002F WARN \u002F FAIL \u002F NOT_APPLICABLE \u002F BLOCKED \u002F ERROR>\n  Reason:  \u003Creason_code, e.g., defense_survives, unresolved_critical>\n\n  Top action items:\n  1. ...\n  2. ...\n  3. ...\n\n  Full report: \u003Cpaper-dir>\u002FKILL_ARGUMENT.md\n```\n\n## Output Contract\n\n- `\u003Cpaper-dir>\u002FKILL_ARGUMENT.md` — human-readable report\n- `\u003Cpaper-dir>\u002FKILL_ARGUMENT.json` — machine-readable ledger\n- `.aris\u002Ftraces\u002Fkill-argument\u002F\u003Cdate>_runNN\u002F` — per-thread codex traces (Attack memo + Adjudication memo)\n- Optional: applied fixes if user explicitly requests; default is **detect-only, do not auto-modify**.\n- `\u003Cpaper-dir>\u002FKILL_ARGUMENT.html` (when `RENDER_HTML = true`, default) — single-file HTML view auto-rendered via `\u002Frender-html` with the JSON sidecar. Full review gate applies. **Non-blocking**: if `\u002Frender-html` fails, the kill-argument verdict still counts as complete.\n\n## Key Rules\n\n- **Fresh agent per call.**  Both Attack and Adjudication use `spawn_agent`, never `send_input`.  Thread 1 and Thread 2 must not share Codex context.\n- **Zero prior context.**  Neither thread receives prior round reviews, fix lists, executor summaries, or improvement-loop logs.\n- **Attack must commit.**  Single argument, ~200 words.  No \"consider also\" hedge.  The whole value is in forcing the reviewer to pick the most damaging line.\n- **Adjudicator must classify, not minimize.**  `still_unresolved` is honest if the paper has no effective response.  Don't downgrade to `partially_answered` unless evidence is real.\n- **Author-chosen positions** (e.g., deliberate title scope, deliberate omission of qualifier): mark `partially_answered` with note that the position is intentional, AND say whether the position is sustainable under the attack.  Don't auto-grade as `answered_by_current_text` just because it's intentional.\n- **Verdict is computed by the skill, not by the adjudicator.**  The Codex thread emits per-point classifications; the skill code maps those to one of the 6 audit verdicts via the table in Step 4.  Never let the adjudicator self-grade the top-level verdict.\n- **Detect-only by direct invocation; can be invoked by `\u002Fauto-paper-improvement-loop` Step 5.5 which then merges unresolved findings into its fix list.**  When a user runs `\u002Fkill-argument paper\u002F` directly, the output is informational and the human decides whether to act.  When the skill is invoked from inside the auto-improvement loop, the loop reads `KILL_ARGUMENT.json`, deduplicates against its existing weakness list, and feeds novel `still_unresolved` points into Step 6 fixes — `\u002Fkill-argument` itself never edits paper files.\n\n## When NOT to Use\n\n- Empirical papers without theorems \u002F scope claims — `\u002Fresearch-review` is more useful.  The skill emits `NOT_APPLICABLE` with `reason_code: not_theory_or_scope_paper` in this case.\n- Very early drafts where the headline isn't stable yet — fix the headline first.  The skill emits `NOT_APPLICABLE` with `reason_code: headline_unstable` if the title or abstract changed within the last 2 commits.\n- Papers with ongoing experiments — wait until results stabilize, then run.\n- (`\u002Fauto-paper-improvement-loop` Step 5.5 used to run this protocol inline; as of May 2026 it now invokes `\u002Fkill-argument` and reads `KILL_ARGUMENT.json` instead, so there is no longer a \"do not invoke from inside auto-loop\" exclusion.)\n\n## Review Tracing\n\nAfter each `spawn_agent` reviewer call, save the trace following `shared-references\u002Freview-tracing.md` (Policy C — forensic; never silently skip).  Use `save_trace.sh` (resolved per the chain in `shared-references\u002Fintegration-contract.md` §2) or write files directly to `.aris\u002Ftraces\u002Fkill-argument\u002F\u003Cdate>_run\u003CNN>\u002F`.  Both threads' raw responses should be preserved.\n\n## Notes\n\nThis skill was extracted as a standalone primitive from `\u002Fauto-paper-improvement-loop` Step 5.5 in May 2026, after the protocol proved valuable in surfacing headline-vs-body scope gaps that score-based reviews missed.  The attack-then-defense pattern was kept exactly because of empirical evidence that asking one model to \"write the rejection memo\" produces qualitatively different feedback than asking it to \"review and grade\" — the former forces commitment, the latter encourages hedging.\n","# Kill Argument Exercise: Adversarial Attack-Defense Review\n\n> **Codex assurance:** both fresh agents are OpenAI-family, so the base JSON\n> records `review_independence: same-family` and\n> `acceptance_status: provisional`. The mechanical count mapping may drive the\n> next step, but it is not cross-family acceptance. Call failure emits ERROR.\n\nStress-test the headline claims of a paper against the strongest possible rejection argument: **$ARGUMENTS**\n\n## Why This Exists\n\nStandard score-based reviews (`\u002Fresearch-review`, `\u002Fauto-paper-improvement-loop`) tend to produce **balanced** weakness lists.  Each weakness gets ~equal attention, ranked CRITICAL > MAJOR > MINOR.  Empirically, this misses one specific failure mode: the **single most damaging argument** a reviewer would write in a rejection paragraph — the one sentence that, if a senior area chair reads it, kills the paper.\n\nA balanced reviewer might list \"scope-overclaim risk\" as MAJOR alongside 3-5 other MAJORs, never quite committing.  An adversarial reviewer **must commit**: their entire job is to convince the area chair to reject in 200 words.\n\nThis skill runs that adversarial pass deliberately, then forces a second fresh reviewer to defend point-by-point, classify each rejection as already-fixed \u002F partially-fixed \u002F still-unresolved, and surface what's actually load-bearing.\n\n**Empirical motivation:** in a real submission run, after several rounds of standard improvement (score 7-8\u002F10), the kill-argument exercise surfaced framing weaknesses that no prior review caught (e.g., a setting being mostly conditional rather than truly general, or a baseline being irrelevant to real systems).  Author rebuttal forced explicit scope qualifications in abstract and discussion that weren't visible from the score-based reviews alone.\n\n## How This Differs From Other Review Skills\n\n| Skill | What it asks the reviewer | Output |\n|-------|---------------------------|--------|\n| Standard peer review | \"Score this paper, list weaknesses by severity\" | balanced weakness list |\n| `\u002Fresearch-review` | \"Deep technical review of methods + claims\" | structured deep critique |\n| `\u002Fproof-checker` | \"Is this theorem actually proved?\" | per-step proof obligation audit |\n| `\u002Fpaper-claim-audit` | \"Does the paper report numbers truthfully?\" | per-claim evidence verification |\n| `\u002Fcitation-audit` | \"Are citations real and used in correct context?\" | per-entry KEEP\u002FFIX\u002FREPLACE\u002FREMOVE |\n| **`\u002Fkill-argument`** | **\"Write the single strongest rejection paragraph; then defend it.\"** | **attack memo + per-point defense + unresolved surfaced** |\n\nThis skill is **complementary**, not a replacement.  Run after standard reviews when you want to know what the worst-case reviewer paragraph would look like, before camera-ready or rebuttal preparation.\n\n## When To Use\n\n- After 1-2 rounds of `\u002Fauto-paper-improvement-loop` settled at a stable score, but before submission.  Surfaces what additional fixes would close the headline-attack gap.\n- During rebuttal preparation, to predict reviewer-2's strongest objection so you can prepare the response in advance.\n- For theory papers with a high-level title that may oversimplify the actual theorem (the most common reject-attack pattern).\n- For papers where a reviewer might attack scope, assumption-vs-claim mismatch, missing proof obligations, or evidence-vs-headline gaps.\n\nThis skill is most valuable for **theory papers** with ≥5 theorem-class environments (so the headline depends on real proof obligations).  For empirical papers without theorems, use `\u002Fresearch-review` instead.\n\n## Constants\n\n- **REVIEWER_MODEL** = `gpt-6-astra` (default; specify `gpt-5.4` if you want to fall back to the legacy default). Reviewer reasoning effort = `ultra` for the deep-audit core threads (capability fallback never below `xhigh`).\n- **CONTEXT_POLICY** = `fresh` (REVIEWER_BIAS_GUARD).  Each thread is a fresh `spawn_agent` call.  **Never** use `send_input`.  No prior review summary, fix list, or executor explanation enters either prompt.\n- **ATTACK_LENGTH** = approximately 200 words (do not exceed 250).  Single coherent argument, not a list.\n- **DEFENSE_DECOMPOSITION** = 3-7 atomic rejection points extracted from the attack memo.  Each gets its own classification.\n- **CLASSIFICATION** = `answered_by_current_text` \u002F `partially_answered` \u002F `still_unresolved`.  (Names chosen so the adjudicator does not assume \"fixed\" implies prior history of patching — they read the paper as a fresh reviewer would.)\n- **OUTPUT** = `KILL_ARGUMENT.md` (human-readable) + `KILL_ARGUMENT.json` (machine-readable) in the paper directory.\n- **RENDER_HTML = true** — When `true` (default), auto-render `KILL_ARGUMENT.md` to HTML after writing the report via `\u002Frender-html \"\u003Cpaper-dir>\u002FKILL_ARGUMENT.md\" --json \"\u003Cpaper-dir>\u002FKILL_ARGUMENT.json\"`. Uses **full review gate** (audit-class artifact). Set `false` to skip, or pass `— render html: false`. **Non-blocking**: failures don't invalidate the kill-argument verdict.\n\n## Workflow\n\nThe attack and adjudication calls are fresh, read-only Codex shards. They return\nstructured per-point records with stable `dedup_key` identifiers; neither call\nwrites the paper or emits cross-family acceptance. The parent computes the\ntop-level mapping mechanically and records a same-family provisional verdict.\nIf `spawn_agent` is unavailable, use fresh sequential contexts where supported;\notherwise emit `BLOCKED` rather than inventing a verdict. See\n[`fan-out-pattern.md`](..\u002Fshared-references\u002Ffan-out-pattern.md).\n\n### Step 1: Discover paper files\n\nLocate the paper directory and inventory the source.\n\n```bash\nPAPER_DIR=\"$ARGUMENTS\"   # e.g., paper-overleaf\u002F or paper\u002F\ncd \"$PAPER_DIR\"\n\n# Find the LaTeX entry point\nENTRY=$(grep -lE '^\\\\documentclass' *.tex 2>\u002Fdev\u002Fnull | head -1)\necho \"Entry: $ENTRY\"\n\n# Find all source files codex should read\nfind . -name \"*.tex\" -not -path \".\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull\nfind . -name \"*.bib\" -not -path \".\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull\nfind figures\u002F -name \"*.pdf\" -o -name \"*.png\" 2>\u002Fdev\u002Fnull\nls -la *.pdf 2>\u002Fdev\u002Fnull  # compiled PDF\n```\n\nIf a compiled PDF is missing, the skill should still run on .tex source alone, but the prompt should mention this so the reviewer doesn't waste cycles trying to extract from a non-existent PDF.\n\n### Step 2: Attack memo (Thread 1, fresh codex)\n\nInvoke `spawn_agent` (NOT `send_input`) with the following prompt structure. Use absolute or paper-directory-relative paths inside the prompt; do not rely on a `cwd` parameter.\n\n```\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: ultra\n  message: |\n    You are simulating a hostile NeurIPS \u002F ICLR \u002F ICML reviewer for a paper.\n    This is a kill-argument adversarial check — your task is NOT to give a\n    balanced review but to construct the **single strongest argument for\n    rejecting this paper**.\n\n    ## Files to read\n    - LaTeX entry: \u003CENTRY>\n    - All section files under sections\u002F or wherever they live\n    - Macro files (math_commands.tex, etc.)\n    - Compiled PDF: \u003Cmain.pdf> (if available)\n\n    Read the source carefully. Do not consult any prior reviews, fix lists,\n    or summaries; this must be a fresh, zero-context adversarial pass.\n\n    ## Your task\n    Construct the single best argument to reject this paper in approximately\n    200 words. Your goal is to write the worst-case rejection memo a senior\n    NeurIPS area chair would produce after reading the paper.\n\n    Focus on these axes (pick the most damaging combination, do not list all):\n    1. Theorem validity: are central theorems actually proved as stated?\n    2. Assumption-vs-claim mismatch: does the body silently retreat to a\n       narrower object than the title\u002Fabstract advertise?\n    3. Missing proof obligations: is a fundamental lemma invoked but not\n       proved (e.g., concentration, generic position, prefactor envelope)\n       that the headline depends on?\n    4. Limit-order ambiguity: are limits in K\u002Fn\u002Fd\u002Feps composed in a way the\n       paper does not commit to?\n    5. Claim-vs-evidence gap: is the empirical\u002Fnumerical evidence too narrow\n       to support the breadth of the stated theorem or take-away?\n    6. Scope overclaim: does the title or abstract sell a result substantially\n       broader than what the body proves?\n\n    ## Constraints\n    - Approximately 200 words total (do NOT exceed 250).\n    - Single argument, not a list — pick the most damaging line of attack\n      and develop it.\n    - Cite specific file:line locations or equation numbers when accusing.\n    - Tone: dispassionate but uncompromising. Do NOT hedge. Do NOT acknowledge\n      mitigations the paper might have made elsewhere. This is the rejection\n      paragraph; the defense gets the next pass.\n    - Do NOT reference prior review rounds, fix lists, or any context outside\n      the current paper files.\n\n    Output: just the rejection memo, nothing else.\n```\n\nSave the returned `agent_id` for the trace; do NOT pass it to Thread 2.  Save the attack memo verbatim — both Thread 2 and the human-readable report use it.\n\n### Step 3: Adjudication memo (Thread 2, fresh codex with attack + paper)\n\nInvoke a second `spawn_agent` call (still NOT `send_input` — Thread 2 is independent of Thread 1's Codex agent history):\n\n```\nspawn_agent:\n  model: gpt-6-astra\n  reasoning_effort: ultra\n  message: |\n    You are an independent area-chair adjudicator examining whether the\n    current paper text answers a hostile reviewer's rejection memo.\n    You are NOT the paper's defender — your job is to read the attack\n    point-by-point and rule, from the current source files alone,\n    whether each point stands or falls. Fresh, zero-context adjudication;\n    do not reference any prior reviews \u002F fix lists.\n\n    ## Paper files\n    [list paths same as Step 2]\n\n    ## The hostile reviewer's rejection memo (the \"attack\")\n    > \u003Cattack memo verbatim from Thread 1>\n\n    ## Your task\n    The attack is one continuous argument, but it makes multiple distinct\n    rejection points that you must adjudicate separately. Decompose the\n    attack into its atomic rejection points (3-7 of them), then for each\n    point classify it:\n\n    - answered_by_current_text: the current paper source already mitigates\n      this point (cite specific file:line evidence)\n    - partially_answered: paper has some response but not enough to refute\n      the attack as written\n    - still_unresolved: paper has no effective response\n\n    The label `answered_by_current_text` is intentional — \"fixed\" implies\n    history of patching and biases toward optimism. You are reading the\n    paper as a reviewer would, with no knowledge of prior round drafts.\n\n    For each rejection point, output:\n    ### Point P_n: \u003Cshort label>\n    **Attack claim**: \u003Cthe specific accusation, ~30 words>\n    **Verdict**: answered_by_current_text | partially_answered | still_unresolved\n    **Evidence (or lack of)**: \u003Ccite file:line, ~50 words>\n    **Severity if unresolved**: critical | major | minor\n    **If unresolved, recommended fix**: \u003Cone specific actionable sentence>\n\n    After per-point analysis, output:\n\n    ## Summary\n    Total rejection points: N\n    - answered_by_current_text: X\n    - partially_answered: Y\n    - still_unresolved: Z\n\n    ## Net assessment\n    \u003Cone short paragraph: would this paper survive a senior area-chair read\n    of the attack memo, given only what is in the current source? Be honest —\n    if Y or Z > 0 and they hit the headline, say so.>\n\n    ## Top action items (in priority order, max 3)\n    1. ...\n    2. ...\n    3. ...\n\n    ## Constraints\n    - Do NOT consult any prior round reviews or fix lists. Adjudication must\n      be made strictly from current paper files.\n    - If the paper cannot refute a point, do NOT minimize — keep severity\n      honest.\n    - If a point reflects an author-chosen position (e.g., conscious title\n      scope decision), classify as `partially_answered` with a note that the\n      position is intentional, AND say whether this position is sustainable\n      under the attack — do NOT auto-grade as `answered_by_current_text`\n      just because it is intentional.\n    - Be specific. No flattery, no hedging, no rationalizing on the paper's\n      behalf.\n```\n\nSave the returned `agent_id`.\n\n### Step 4: Write KILL_ARGUMENT.md and KILL_ARGUMENT.json\n\nCompose the human-readable report `\u003Cpaper-dir>\u002FKILL_ARGUMENT.md`:\n\n```markdown\n# Kill Argument Report — \u003Cpaper title>\n\n**Date**: \u003CYYYY-MM-DD>\n**Reviewer model**: gpt-6-astra ultra, fresh agents (no send_input)\n**Attack agent**: \u003Cagent_id 1>\n**Adjudicator agent**: \u003Cagent_id 2>\n**Verdict**: \u003CPASS \u002F WARN \u002F FAIL \u002F NOT_APPLICABLE \u002F BLOCKED \u002F ERROR> (`reason_code: \u003C...>`)\n\n## Net assessment\n\n\u003Cparagraph from adjudicator memo's \"Net assessment\">\n\n## Attack memo (verbatim)\n\n> \u003Cattack memo from Thread 1>\n\n## Adjudication (per-point)\n\n\u003Ccopy verbatim from Thread 2 — uses labels answered_by_current_text \u002F partially_answered \u002F still_unresolved>\n\n## Top action items\n\n\u003Ccopy from Thread 2>\n\n## Recommendation\n\nIf P_4 (or whatever still_unresolved critical) is research-level, record\nit as a known open problem in the conclusion \u002F limitations. If it is\nwriting-level, queue for next \u002Fauto-paper-improvement-loop round.\n```\n\nCompose the machine-readable `\u003Cpaper-dir>\u002FKILL_ARGUMENT.json` per the\nARIS Audit Artifact Schema (`shared-references\u002Fassurance-contract.md`):\n\n```json\n{\n  \"audit_skill\": \"kill-argument\",\n  \"verdict\": \"PASS | WARN | FAIL | NOT_APPLICABLE | BLOCKED | ERROR\",\n  \"reason_code\": \"\u003Csee verdict mapping below>\",\n  \"summary\": \"\u003Cone-line summary, ~80 chars>\",\n  \"audited_input_hashes\": {\n    \"main.tex\":                          \"sha256:\u003C...>\",\n    \"sec\u002F0.abstract.tex\":                \"sha256:\u003C...>\",\n    \"sec\u002F\u003Ceach-section>.tex\":            \"sha256:\u003C...>\",\n    \"references.bib\":                    \"sha256:\u003C...>\",\n    \"main.pdf\":                          \"sha256:\u003C...>\"\n  },\n  \"trace_path\": \".aris\u002Ftraces\u002Fkill-argument\u002F\u003Cdate>_run\u003CNN>\u002F\",\n  \"agent_id\": \"\u003Cdefense agent_id — primary; attack agent_id in details>\",\n  \"executor_model\": \"codex-gpt-6-astra\",\n  \"executor_family\": \"openai\",\n  \"reviewer_model\": \"gpt-6-astra\",\n  \"reviewer_family\": \"openai\",\n  \"review_independence\": \"same-family\",\n  \"acceptance_status\": \"provisional\",\n  \"reviewer_reasoning\": \"ultra\",\n  \"generated_at\": \"\u003CUTC ISO-8601>\",\n  \"details\": {\n    \"attack_agent_id\": \"\u003Cagent_id 1>\",\n    \"defense_agent_id\": \"\u003Cagent_id 2 — same as top-level agent_id>\",\n    \"attack_memo\": \"\u003Cverbatim>\",\n    \"decomposed_points\": [\n      {\n        \"id\": \"P_1\",\n        \"label\": \"\u003Cshort label>\",\n        \"attack_claim\": \"\u003C...>\",\n        \"verdict\": \"answered_by_current_text | partially_answered | still_unresolved\",\n        \"evidence\": \"\u003Cfile:line citation>\",\n        \"severity_if_unresolved\": \"critical | major | minor\",\n        \"recommended_fix\": \"\u003C...>\"\n      }\n    ],\n    \"counts\": {\n      \"answered_by_current_text\": \u003Cint>,\n      \"partially_answered\":       \u003Cint>,\n      \"still_unresolved\":         \u003Cint>\n    },\n    \"net_assessment\": \"\u003Cadjudicator memo's net assessment>\",\n    \"top_action_items\": [\"...\", \"...\", \"...\"]\n  }\n}\n```\n\n**Hash inputs** (`audited_input_hashes`): use paper-relative paths,\n`sha256` of every `.tex` consumed plus `references.bib` and the\ncompiled `main.pdf` if it exists. The verifier rehashes these on\n`verify_paper_audits.sh` and flags `STALE` if the user edited the\npaper after running the audit.\n\n**Verdict mapping** (every (counts, severity) tuple must hit exactly one row):\n\n| Verdict | reason_code | Trigger |\n|---|---|---|\n| `FAIL` | `unresolved_critical` | ≥1 `still_unresolved` at `critical` severity |\n| `WARN` | `unresolved_major_or_minor` | ≥1 `still_unresolved` at `major` or `minor` severity (and no `critical`) |\n| `WARN` | `partial_critical_or_repeated_major` | 0 `still_unresolved`, AND ≥1 `partially_answered` at `critical` or `major` |\n| `PASS` | `defense_survives_with_minor_partial_only` | 0 `still_unresolved`, AND ≥1 `partially_answered`, all at `minor` severity |\n| `PASS` | `defense_survives` | 0 `still_unresolved`, AND 0 `partially_answered` |\n| `NOT_APPLICABLE` | `not_theory_or_scope_paper` | Paper has \u003C2 `\\begin{theorem\\|lemma\\|proposition\\|corollary}` AND no scope \u002F generality claims in abstract |\n| `NOT_APPLICABLE` | `headline_unstable` | Title or abstract changed within the last 2 commits — re-run after headline stabilizes |\n| `BLOCKED` | `paper_compile_failed` | Compiled PDF missing AND `main.tex` does not compile clean — adjudication needs source fidelity |\n| `BLOCKED` | `source_files_missing` | `main.tex` not found, or no `sec\u002F*.tex` files |\n| `ERROR` | `codex_api_error` | `spawn_agent` call failed |\n| `ERROR` | `decomposition_parse_failed` | Adjudicator thread did not return parseable per-point structure |\n| `ERROR` | `trace_save_failed` | Trace directory write failed |\n\n`PASS` requires `still_unresolved == 0`. With `still_unresolved == 0`, any\n`partially_answered` at `major` or higher makes the best available verdict\n`WARN` — never `PASS`.\n\nThe verdict is computed from the per-point counts; do NOT let the\ndefense thread output the top-level verdict directly (that would let\nit self-grade). The skill code does the verdict mapping.\n\n### Step 5: Print summary\n\nTo the user:\n\n```\n🗡  Kill Argument complete.\n\n  Attack: \u003Cone-sentence summary of the rejection thrust>\n\n  Adjudication breakdown:\n    answered_by_current_text:   X\n    partially_answered:         Y\n    still_unresolved:           Z   ← critical: \u003Cnames>\n\n  Verdict: \u003CPASS \u002F WARN \u002F FAIL \u002F NOT_APPLICABLE \u002F BLOCKED \u002F ERROR>\n  Reason:  \u003Creason_code, e.g., defense_survives, unresolved_critical>\n\n  Top action items:\n  1. ...\n  2. ...\n  3. ...\n\n  Full report: \u003Cpaper-dir>\u002FKILL_ARGUMENT.md\n```\n\n## Output Contract\n\n- `\u003Cpaper-dir>\u002FKILL_ARGUMENT.md` — human-readable report\n- `\u003Cpaper-dir>\u002FKILL_ARGUMENT.json` — machine-readable ledger\n- `.aris\u002Ftraces\u002Fkill-argument\u002F\u003Cdate>_runNN\u002F` — per-thread codex traces (Attack memo + Adjudication memo)\n- Optional: applied fixes if user explicitly requests; default is **detect-only, do not auto-modify**.\n- `\u003Cpaper-dir>\u002FKILL_ARGUMENT.html` (when `RENDER_HTML = true`, default) — single-file HTML view auto-rendered via `\u002Frender-html` with the JSON sidecar. Full review gate applies. **Non-blocking**: if `\u002Frender-html` fails, the kill-argument verdict still counts as complete.\n\n## Key Rules\n\n- **Fresh agent per call.**  Both Attack and Adjudication use `spawn_agent`, never `send_input`.  Thread 1 and Thread 2 must not share Codex context.\n- **Zero prior context.**  Neither thread receives prior round reviews, fix lists, executor summaries, or improvement-loop logs.\n- **Attack must commit.**  Single argument, ~200 words.  No \"consider also\" hedge.  The whole value is in forcing the reviewer to pick the most damaging line.\n- **Adjudicator must classify, not minimize.**  `still_unresolved` is honest if the paper has no effective response.  Don't downgrade to `partially_answered` unless evidence is real.\n- **Author-chosen positions** (e.g., deliberate title scope, deliberate omission of qualifier): mark `partially_answered` with note that the position is intentional, AND say whether the position is sustainable under the attack.  Don't auto-grade as `answered_by_current_text` just because it's intentional.\n- **Verdict is computed by the skill, not by the adjudicator.**  The Codex thread emits per-point classifications; the skill code maps those to one of the 6 audit verdicts via the table in Step 4.  Never let the adjudicator self-grade the top-level verdict.\n- **Detect-only by direct invocation; can be invoked by `\u002Fauto-paper-improvement-loop` Step 5.5 which then merges unresolved findings into its fix list.**  When a user runs `\u002Fkill-argument paper\u002F` directly, the output is informational and the human decides whether to act.  When the skill is invoked from inside the auto-improvement loop, the loop reads `KILL_ARGUMENT.json`, deduplicates against its existing weakness list, and feeds novel `still_unresolved` points into Step 6 fixes — `\u002Fkill-argument` itself never edits paper files.\n\n## When NOT to Use\n\n- Empirical papers without theorems \u002F scope claims — `\u002Fresearch-review` is more useful.  The skill emits `NOT_APPLICABLE` with `reason_code: not_theory_or_scope_paper` in this case.\n- Very early drafts where the headline isn't stable yet — fix the headline first.  The skill emits `NOT_APPLICABLE` with `reason_code: headline_unstable` if the title or abstract changed within the last 2 commits.\n- Papers with ongoing experiments — wait until results stabilize, then run.\n- (`\u002Fauto-paper-improvement-loop` Step 5.5 used to run this protocol inline; as of May 2026 it now invokes `\u002Fkill-argument` and reads `KILL_ARGUMENT.json` instead, so there is no longer a \"do not invoke from inside auto-loop\" exclusion.)\n\n## Review Tracing\n\nAfter each `spawn_agent` reviewer call, save the trace following `shared-references\u002Freview-tracing.md` (Policy C — forensic; never silently skip).  Use `save_trace.sh` (resolved per the chain in `shared-references\u002Fintegration-contract.md` §2) or write files directly to `.aris\u002Ftraces\u002Fkill-argument\u002F\u003Cdate>_run\u003CNN>\u002F`.  Both threads' raw responses should be preserved.\n\n## Notes\n\nThis skill was extracted as a standalone primitive from `\u002Fauto-paper-improvement-loop` Step 5.5 in May 2026, after the protocol proved valuable in surfacing headline-vs-body scope gaps that score-based reviews missed.  The attack-then-defense pattern was kept exactly because of empirical evidence that asking one model to \"write the rejection memo\" produces qualitatively different feedback than asking it to \"review and grade\" — the former forces commitment, the latter encourages hedging.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob, spawn_agent","[paper-directory]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fkill-argument",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill kill-argument",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill kill-argument",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill kill-argument","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fkill-argument\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]