[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AP7ZR10RDRW06CWFWS0MRY":3,"skill-same:01M7AP7ZR10RDRW06CWFWS0MRY":132},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7AP7ZR10RDRW06CWFWS0MRY","solidity-auditor",null,"Security audit of Solidity code while you develop. Trigger on \"audit\", \"check this contract\", \"review for security\". Modes - default (full repo) or a specific filename.","wildcat-finance\u002Fskills","wildcat-finance","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113041915?v=4","01M7AP0V1G8X0SWHP6C5V90RM5","The Wildcat Protocol","01M7AP0V24Y50BGVCQ4DV496VD",13,"MIT","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: solidity-auditor\ndescription: Security audit of Solidity code while you develop. Trigger on \"audit\", \"check this contract\", \"review for security\". Modes - default (full repo) or a specific filename.\n---\n\n# Smart Contract Security Audit\n\nYou are the orchestrator of a parallelized smart contract security audit.\n\n## Mode Selection\n\n**Exclude pattern:** skip directories `interfaces\u002F`, `lib\u002F`, `mocks\u002F`, `test\u002F` and files matching `*.t.sol`, `*Test*.sol` or `*Mock*.sol`.\n\n- **Default** (no arguments): scan all `.sol` files using the exclude pattern. Use Bash `find` (not Glob).\n- **`$filename ...`**: scan the specified file(s) only.\n\n**Flags:**\n\n- `--file-output` (off by default): also write the report to a markdown file (path per `{resolved_path}\u002Freport-formatting.md`). Never write a report file unless explicitly passed.\n## Orchestration\n\n**Turn 1 — Discover.** Print the banner, then make these parallel tool calls in one message:\n\na. Bash `find` for in-scope `.sol` files per mode selection\nb. Glob for `**\u002Freferences\u002Fhacking-agents\u002Fshared-rules.md` — extract the `references\u002F` directory (two levels up) as `{resolved_path}`\nc. ToolSearch `select:Agent`\nd. Read the local `VERSION` file from the same directory as this skill\ne. Bash `curl -sf https:\u002F\u002Fraw.githubusercontent.com\u002Fpashov\u002Fskills\u002Fmain\u002Fsolidity-auditor\u002FVERSION`\nf. Bash `mktemp -d .\u002F.audit-XXXXXX` → store as `{bundle_dir}`\n\nIf the remote VERSION fetch succeeds and differs from local, print `⚠️ You are not using the latest version. Please upgrade for best security coverage. See https:\u002F\u002Fgithub.com\u002Fpashov\u002Fskills`. If it fails, skip silently.\n\n**Turn 1b — Model selection (Claude Code only).** This turn applies ONLY when both `AskUserQuestion` and the `Agent` tool (with a `model` parameter) are available in your runtime — i.e., Claude Code. On Codex, Gemini, Cursor's native agent, or any runtime without these, SKIP this turn entirely, leave `{agent_model}` unset, and proceed to Turn 2. Do NOT emit the question as prose. Do NOT substitute any other mechanism.\n\nOn Claude Code:\n\n1. Read your system prompt to detect your own model **family** (Opus, Sonnet, or Haiku). Ignore the version digits — the Agent tool's `model` parameter takes the family name (`\"opus\"` \u002F `\"sonnet\"` \u002F `\"haiku\"`), and the runtime resolves to the latest version in that family.\n2. Call `AskUserQuestion` with:\n   - Question: `\"Which Claude model should the 12 audit agents use?\"`\n   - Three single-select options. Mark the orchestrator's own family as `(Recommended)` and place it first.\n   - On each option, set the `description` field to `latest`.\n   - On each option, set the `preview` field verbatim (preserve all whitespace exactly — the box widths must stay equal across all three):\n\n   Opus preview:\n\n   ```\n   ┌──────────────────────────────────────────────────────────┐\n   │  opus  ·  highest reasoning  ·  most expensive           │\n   └──────────────────────────────────────────────────────────┘\n   ```\n\n   Sonnet preview:\n\n   ```\n   ┌──────────────────────────────────────────────────────────┐\n   │  sonnet  ·  balanced reasoning  ·  mid cost              │\n   └──────────────────────────────────────────────────────────┘\n   ```\n\n   Haiku preview:\n\n   ```\n   ┌──────────────────────────────────────────────────────────┐\n   │  haiku  ·  lowest reasoning  ·  cheapest                 │\n   └──────────────────────────────────────────────────────────┘\n   ```\n3. Store the runner's choice as `{agent_model}`. If no answer, default to the orchestrator's own model.\n\n**Turn 2 — Prepare.** In one message, make parallel tool calls: (a) Read `{resolved_path}\u002Freport-formatting.md`, (b) Read `{resolved_path}\u002Fjudging.md`.\n\nThen build all bundles in a single Bash command using `cat` (not shell variables or heredocs):\n\n1. `{bundle_dir}\u002Fsource.md` — ALL in-scope `.sol` files, each with a `### path` header and fenced code block.\n2. Agent bundles = `source.md` + agent-specific files:\n\n| Bundle                | Appended files (relative to `{resolved_path}`)                                                                                                |\n| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |\n| `agent-1-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fmath-precision-agent.md` + `hacking-agents\u002Fshared-rules.md`                            |\n| `agent-2-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Faccess-control-agent.md` + `hacking-agents\u002Fshared-rules.md`                            |\n| `agent-3-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Feconomic-security-agent.md` + `hacking-agents\u002Fshared-rules.md`                         |\n| `agent-4-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fexecution-trace-agent.md` + `hacking-agents\u002Fshared-rules.md`                           |\n| `agent-5-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Finvariant-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-6-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fperiphery-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-7-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Ffirst-principles-agent.md` + `hacking-agents\u002Fshared-rules.md`                          |\n| `agent-8-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fasymmetry-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-9-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fboundary-agent.md` + `hacking-agents\u002Fshared-rules.md`                                  |\n| `agent-10-bundle.md`  | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fnumerical-gap-agent.md` + `hacking-agents\u002Fshared-rules.md`                             |\n| `agent-11-bundle.md`  | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Ftrust-gap-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-12-bundle.md`  | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fflow-gap-agent.md` + `hacking-agents\u002Fshared-rules.md`                                  |\n\nEach bundle = source.md + SOP + specialty + shared-rules. Agents read the bundle; no Read\u002FGrep needed for the initial scan. Targeted Read\u002FGrep allowed for cross-file investigation.\n\nPrint line counts for every bundle and `source.md`. Do NOT inline source code into the Agent call prompt itself.\n\n**Turn 3a — Spawn all 12 agents.** In one message, spawn all 12 agents as **parallel BACKGROUND Agent calls** (`run_in_background=true`). If Turn 1b set `{agent_model}`, pass `model={agent_model}` on every Agent call. If `{agent_model}` is unset (Turn 1b skipped — Codex, Gemini, others), omit the `model` parameter entirely — do NOT substitute any default. The orchestrator will receive a notification when each agent completes — do NOT poll or sleep. Single phase, no later spawns. Proceed to Turn 3b only after all 12 have notified completion.\n\nAgents 1–9 use the **single-specialty prompt** (Turn 3a-i). Agents 10–12 use the **gap-hunter prompt** (Turn 3a-ii).\n\n**Turn 3a-i — Single-specialty prompt template (agents 1–9, substitute real values):**\n\n```\nYou are an attacker. Your specialty, mindset, source, and output rules\nare in your bundle. Read it fully before producing findings.\n\nRead first:\n- {bundle_dir}\u002Fagent-N-bundle.md (XXXX lines) — source + SOP + specialty + shared rules.\n\nThe bundle contains all in-scope source. Do NOT re-read in-scope files\nfor the initial scan. Use Read\u002FGrep only for cross-file searches or\nout-of-scope context (interfaces\u002F, lib\u002F, mocks\u002F, test\u002F).\n\nWhat a finding looks like:\n- file, function\n- root cause — the one-sentence code-level defect\n- minimal fix — the smallest change that eliminates the defect\n- proof — concrete numbers, a trace, or quoted code\n\nWithout concrete proof, it's a LEAD, not a finding. Leads are honest\nabout what you couldn't verify — they're not failures, they're\ncalibration. Emit them.\n\nDon't skim. Don't trust your first read. Trust your discomfort.\n\nOutput format: see shared-rules.md inside your bundle.\n```\n\n**Turn 3a-ii — Gap-hunter prompt template (agents 10–12, substitute real values):**\n\n```\nYou are an attacker. Your gap-hunter specialty, mindset, source, and\noutput rules are in your bundle. Read it fully before producing findings.\n\nRead first:\n- {bundle_dir}\u002Fagent-N-bundle.md (XXXX lines) — source + SOP + gap-hunter specialty + shared rules.\n\nThe bundle contains all in-scope source. Do NOT re-read in-scope files\nfor the initial scan. Use Read\u002FGrep only for cross-file searches or\nout-of-scope context (interfaces\u002F, lib\u002F, mocks\u002F, test\u002F).\n\nWhat a finding looks like:\n- file, function\n- seam — which two or three lenses combine\n- root cause — the one-sentence code-level defect that lives at the seam\n- minimal fix — the smallest change that eliminates the defect\n- proof — concrete numbers, a trace, or quoted code showing the seam\n\nWithout concrete proof of the seam, it's a LEAD, not a finding.\nLeads are honest about what you couldn't verify — they're not failures,\nthey're calibration. Emit them.\n\nDon't skim. Don't trust your first read. Trust your discomfort.\n\nOutput format: see shared-rules.md inside your bundle (gap-hunter-specific\noutput fields are in your specialty file).\n```\n\n**Turn 3b — Wait for all 12 agents to complete.** Once every one of the 12 spawned agents has notified completion, proceed to Turn 4. Do NOT proceed to dedup until every agent has finished — let them run to natural completion. Do NOT poll or sleep; act only on completion notifications.\n\n**Turn 4 — Deduplicate, validate & output.** Single-pass: deduplicate all agent results, gate-evaluate, and produce the final report in one turn. Do NOT print an intermediate dedup list — go straight to the report.\n\n1. **Dedup.** Parse every FINDING and LEAD from the 12 agents. Group by `group_key` (Contract | function | bug-class). Exact-match first; merge synonymous bug_class within same (Contract, function). Keep best per group, number sequentially, annotate `[agents: N]`.\n\n   **MANDATORY — Wide-description (group_key).** Merged group with distinct mechanisms (different `fix:`, code-level cause, or attack path) MUST list every mechanism. No dropping. Same function can have multiple coexisting bugs at the same group_key — all MUST appear.\n\n   **MANDATORY — Function-level second pass (after group_key dedup).** Run at (Contract, function), ignoring bug_class. Agents often label coexisting bugs with different bug_class tags but reference multiple mechanisms in the body. For every (Contract, function) with multiple final findings: scan body (description, path, proof, fix) of every constituent for distinct mechanisms across bug_class boundaries. Every mechanism in any constituent body MUST appear in ≥1 final finding.\n\n   **MANDATORY — Function isolation (HARD).** NEVER merge across different `function:` fields. Dedup only within (Contract, function). Different function = different bug. Second pass above stays WITHIN (Contract, function), never across.\n\n   **MANDATORY — Fix preservation (HARD GATE).** Before writing merged `fix:` on a multi-finding (Contract, function):\n   1. Collect every raw `fix:` from agents flagging the tuple.\n   2. Group by ADD-lines (`+` lines, or equivalent require\u002Fassignment).\n   3. Distinct if ADD-lines differ in: called function\u002Fexpression (e.g., `require(msg.value == amount)` vs `require(zrc20 != _ETH_ADDRESS_)`), check direction (validate\u002Frestrict\u002Fban), or checked parameter.\n   4. ≥2 distinct → present as Option A, B, … — one block per distinct fix, verbatim from agent text (no paraphrase).\n   5. Label intuitively: validate \u002F restrict \u002F allow-and-handle \u002F ban-path.\n\n   **Output format when 2+ distinct fixes exist:**\n\n   ```\n   **Fix (Option A — \u003Clabel>)**:\n\n   ```diff\n   \u003Cverbatim diff from raw agent N1's fix>\n   ```\n\n   **Fix (Option B — \u003Clabel>)**:\n\n   ```diff\n   \u003Cverbatim diff from raw agent N2's fix>\n   ```\n   ```\n\n   **Inline check before printing**: count distinct fixes from raw for this (Contract, function). ≥2 distinct but merged shows 1 → violation, add alternatives.\n\n   **MANDATORY — Completeness (HARD GATE).** Before print: list every unique (Contract, function, bug-class) in any raw FINDING\u002FLEAD across the 12 agents. Every unique (Contract, function) MUST have ≥1 item in final. Zero = silent drop, fix it. Multiple bug-class within same (Contract, function) MAY collapse to one item (wide-description), but the (Contract, function) MUST survive. Print inline before report: `Completeness: N unique (Contract, function) in raw, N covered in final.`\n\n   Composite chains: if A's output feeds B's precondition AND combined impact > either alone, add `Chain: [A] + [B]` at conf = min(A, B). Most audits: 0–2.\n\n2. **Gate.** Run each deduped finding through the four gates in `judging.md` (no skip, no reorder, no revisit after verdict).\n\n   **Single-pass:** every relevant code path ONCE in fixed order (constructor → setters → swap → mint → burn → liquidate). One-line verdict: `BLOCKS` \u002F `ALLOWS` \u002F `IRRELEVANT` \u002F `UNCERTAIN`. `UNCERTAIN = ALLOWS`. Commit, no re-examination.\n\n3. **Lead promotion \u002F rejection.**\n   - LEAD → FINDING (conf 75) if: full exploit chain in source, OR `[agents: 2+]` demoted (not rejected) same issue.\n   - `[agents: 2+]` does NOT override a code path that interrupts attack before harm — demote to LEAD if execution uncertain.\n   - No deployer-intent reasoning — what code allows, not how deployer might use it.\n\n4. **Format\u002Fprint** per `report-formatting.md`. Exclude rejected. If `--file-output`: also write to file. Do NOT re-read source to \"verify the most critical claim\" — agents did that, dedup filtered. Re-verification costs ~5min, rarely changes verdicts. Skip.\n\n5. **Auto-clean.** After print (and `--file-output` write): `rm -rf {bundle_dir}`. Bundle dir = transient build state, not an artifact. Don't skip. For debugging: copy bundle elsewhere before re-running.\n\n\n## Banner\n\nBefore doing anything else, print this exactly:\n\n```\n\n██████╗  █████╗ ███████╗██╗  ██╗ ██████╗ ██╗   ██╗     ███████╗██╗  ██╗██╗██╗     ██╗     ███████╗\n██╔══██╗██╔══██╗██╔════╝██║  ██║██╔═══██╗██║   ██║     ██╔════╝██║ ██╔╝██║██║     ██║     ██╔════╝\n██████╔╝███████║███████╗███████║██║   ██║██║   ██║     ███████╗█████╔╝ ██║██║     ██║     ███████╗\n██╔═══╝ ██╔══██║╚════██║██╔══██║██║   ██║╚██╗ ██╔╝     ╚════██║██╔═██╗ ██║██║     ██║     ╚════██║\n██║     ██║  ██║███████║██║  ██║╚██████╔╝ ╚████╔╝      ███████║██║  ██╗██║███████╗███████╗███████║\n╚═╝     ╚═╝  ╚═╝╚══════╝╚═╝  ╚═╝ ╚═════╝   ╚═══╝       ╚══════╝╚═╝  ╚═╝╚═╝╚══════╝╚══════╝╚══════╝\n\n```\n","# Smart Contract Security Audit\n\nYou are the orchestrator of a parallelized smart contract security audit.\n\n## Mode Selection\n\n**Exclude pattern:** skip directories `interfaces\u002F`, `lib\u002F`, `mocks\u002F`, `test\u002F` and files matching `*.t.sol`, `*Test*.sol` or `*Mock*.sol`.\n\n- **Default** (no arguments): scan all `.sol` files using the exclude pattern. Use Bash `find` (not Glob).\n- **`$filename ...`**: scan the specified file(s) only.\n\n**Flags:**\n\n- `--file-output` (off by default): also write the report to a markdown file (path per `{resolved_path}\u002Freport-formatting.md`). Never write a report file unless explicitly passed.\n## Orchestration\n\n**Turn 1 — Discover.** Print the banner, then make these parallel tool calls in one message:\n\na. Bash `find` for in-scope `.sol` files per mode selection\nb. Glob for `**\u002Freferences\u002Fhacking-agents\u002Fshared-rules.md` — extract the `references\u002F` directory (two levels up) as `{resolved_path}`\nc. ToolSearch `select:Agent`\nd. Read the local `VERSION` file from the same directory as this skill\ne. Bash `curl -sf https:\u002F\u002Fraw.githubusercontent.com\u002Fpashov\u002Fskills\u002Fmain\u002Fsolidity-auditor\u002FVERSION`\nf. Bash `mktemp -d .\u002F.audit-XXXXXX` → store as `{bundle_dir}`\n\nIf the remote VERSION fetch succeeds and differs from local, print `⚠️ You are not using the latest version. Please upgrade for best security coverage. See https:\u002F\u002Fgithub.com\u002Fpashov\u002Fskills`. If it fails, skip silently.\n\n**Turn 1b — Model selection (Claude Code only).** This turn applies ONLY when both `AskUserQuestion` and the `Agent` tool (with a `model` parameter) are available in your runtime — i.e., Claude Code. On Codex, Gemini, Cursor's native agent, or any runtime without these, SKIP this turn entirely, leave `{agent_model}` unset, and proceed to Turn 2. Do NOT emit the question as prose. Do NOT substitute any other mechanism.\n\nOn Claude Code:\n\n1. Read your system prompt to detect your own model **family** (Opus, Sonnet, or Haiku). Ignore the version digits — the Agent tool's `model` parameter takes the family name (`\"opus\"` \u002F `\"sonnet\"` \u002F `\"haiku\"`), and the runtime resolves to the latest version in that family.\n2. Call `AskUserQuestion` with:\n   - Question: `\"Which Claude model should the 12 audit agents use?\"`\n   - Three single-select options. Mark the orchestrator's own family as `(Recommended)` and place it first.\n   - On each option, set the `description` field to `latest`.\n   - On each option, set the `preview` field verbatim (preserve all whitespace exactly — the box widths must stay equal across all three):\n\n   Opus preview:\n\n   ```\n   ┌──────────────────────────────────────────────────────────┐\n   │  opus  ·  highest reasoning  ·  most expensive           │\n   └──────────────────────────────────────────────────────────┘\n   ```\n\n   Sonnet preview:\n\n   ```\n   ┌──────────────────────────────────────────────────────────┐\n   │  sonnet  ·  balanced reasoning  ·  mid cost              │\n   └──────────────────────────────────────────────────────────┘\n   ```\n\n   Haiku preview:\n\n   ```\n   ┌──────────────────────────────────────────────────────────┐\n   │  haiku  ·  lowest reasoning  ·  cheapest                 │\n   └──────────────────────────────────────────────────────────┘\n   ```\n3. Store the runner's choice as `{agent_model}`. If no answer, default to the orchestrator's own model.\n\n**Turn 2 — Prepare.** In one message, make parallel tool calls: (a) Read `{resolved_path}\u002Freport-formatting.md`, (b) Read `{resolved_path}\u002Fjudging.md`.\n\nThen build all bundles in a single Bash command using `cat` (not shell variables or heredocs):\n\n1. `{bundle_dir}\u002Fsource.md` — ALL in-scope `.sol` files, each with a `### path` header and fenced code block.\n2. Agent bundles = `source.md` + agent-specific files:\n\n| Bundle                | Appended files (relative to `{resolved_path}`)                                                                                                |\n| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |\n| `agent-1-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fmath-precision-agent.md` + `hacking-agents\u002Fshared-rules.md`                            |\n| `agent-2-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Faccess-control-agent.md` + `hacking-agents\u002Fshared-rules.md`                            |\n| `agent-3-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Feconomic-security-agent.md` + `hacking-agents\u002Fshared-rules.md`                         |\n| `agent-4-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fexecution-trace-agent.md` + `hacking-agents\u002Fshared-rules.md`                           |\n| `agent-5-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Finvariant-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-6-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fperiphery-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-7-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Ffirst-principles-agent.md` + `hacking-agents\u002Fshared-rules.md`                          |\n| `agent-8-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fasymmetry-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-9-bundle.md`   | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fboundary-agent.md` + `hacking-agents\u002Fshared-rules.md`                                  |\n| `agent-10-bundle.md`  | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fnumerical-gap-agent.md` + `hacking-agents\u002Fshared-rules.md`                             |\n| `agent-11-bundle.md`  | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Ftrust-gap-agent.md` + `hacking-agents\u002Fshared-rules.md`                                 |\n| `agent-12-bundle.md`  | `source.md` + `senior-auditor-sop.md` + `hacking-agents\u002Fflow-gap-agent.md` + `hacking-agents\u002Fshared-rules.md`                                  |\n\nEach bundle = source.md + SOP + specialty + shared-rules. Agents read the bundle; no Read\u002FGrep needed for the initial scan. Targeted Read\u002FGrep allowed for cross-file investigation.\n\nPrint line counts for every bundle and `source.md`. Do NOT inline source code into the Agent call prompt itself.\n\n**Turn 3a — Spawn all 12 agents.** In one message, spawn all 12 agents as **parallel BACKGROUND Agent calls** (`run_in_background=true`). If Turn 1b set `{agent_model}`, pass `model={agent_model}` on every Agent call. If `{agent_model}` is unset (Turn 1b skipped — Codex, Gemini, others), omit the `model` parameter entirely — do NOT substitute any default. The orchestrator will receive a notification when each agent completes — do NOT poll or sleep. Single phase, no later spawns. Proceed to Turn 3b only after all 12 have notified completion.\n\nAgents 1–9 use the **single-specialty prompt** (Turn 3a-i). Agents 10–12 use the **gap-hunter prompt** (Turn 3a-ii).\n\n**Turn 3a-i — Single-specialty prompt template (agents 1–9, substitute real values):**\n\n```\nYou are an attacker. Your specialty, mindset, source, and output rules\nare in your bundle. Read it fully before producing findings.\n\nRead first:\n- {bundle_dir}\u002Fagent-N-bundle.md (XXXX lines) — source + SOP + specialty + shared rules.\n\nThe bundle contains all in-scope source. Do NOT re-read in-scope files\nfor the initial scan. Use Read\u002FGrep only for cross-file searches or\nout-of-scope context (interfaces\u002F, lib\u002F, mocks\u002F, test\u002F).\n\nWhat a finding looks like:\n- file, function\n- root cause — the one-sentence code-level defect\n- minimal fix — the smallest change that eliminates the defect\n- proof — concrete numbers, a trace, or quoted code\n\nWithout concrete proof, it's a LEAD, not a finding. Leads are honest\nabout what you couldn't verify — they're not failures, they're\ncalibration. Emit them.\n\nDon't skim. Don't trust your first read. Trust your discomfort.\n\nOutput format: see shared-rules.md inside your bundle.\n```\n\n**Turn 3a-ii — Gap-hunter prompt template (agents 10–12, substitute real values):**\n\n```\nYou are an attacker. Your gap-hunter specialty, mindset, source, and\noutput rules are in your bundle. Read it fully before producing findings.\n\nRead first:\n- {bundle_dir}\u002Fagent-N-bundle.md (XXXX lines) — source + SOP + gap-hunter specialty + shared rules.\n\nThe bundle contains all in-scope source. Do NOT re-read in-scope files\nfor the initial scan. Use Read\u002FGrep only for cross-file searches or\nout-of-scope context (interfaces\u002F, lib\u002F, mocks\u002F, test\u002F).\n\nWhat a finding looks like:\n- file, function\n- seam — which two or three lenses combine\n- root cause — the one-sentence code-level defect that lives at the seam\n- minimal fix — the smallest change that eliminates the defect\n- proof — concrete numbers, a trace, or quoted code showing the seam\n\nWithout concrete proof of the seam, it's a LEAD, not a finding.\nLeads are honest about what you couldn't verify — they're not failures,\nthey're calibration. Emit them.\n\nDon't skim. Don't trust your first read. Trust your discomfort.\n\nOutput format: see shared-rules.md inside your bundle (gap-hunter-specific\noutput fields are in your specialty file).\n```\n\n**Turn 3b — Wait for all 12 agents to complete.** Once every one of the 12 spawned agents has notified completion, proceed to Turn 4. Do NOT proceed to dedup until every agent has finished — let them run to natural completion. Do NOT poll or sleep; act only on completion notifications.\n\n**Turn 4 — Deduplicate, validate & output.** Single-pass: deduplicate all agent results, gate-evaluate, and produce the final report in one turn. Do NOT print an intermediate dedup list — go straight to the report.\n\n1. **Dedup.** Parse every FINDING and LEAD from the 12 agents. Group by `group_key` (Contract | function | bug-class). Exact-match first; merge synonymous bug_class within same (Contract, function). Keep best per group, number sequentially, annotate `[agents: N]`.\n\n   **MANDATORY — Wide-description (group_key).** Merged group with distinct mechanisms (different `fix:`, code-level cause, or attack path) MUST list every mechanism. No dropping. Same function can have multiple coexisting bugs at the same group_key — all MUST appear.\n\n   **MANDATORY — Function-level second pass (after group_key dedup).** Run at (Contract, function), ignoring bug_class. Agents often label coexisting bugs with different bug_class tags but reference multiple mechanisms in the body. For every (Contract, function) with multiple final findings: scan body (description, path, proof, fix) of every constituent for distinct mechanisms across bug_class boundaries. Every mechanism in any constituent body MUST appear in ≥1 final finding.\n\n   **MANDATORY — Function isolation (HARD).** NEVER merge across different `function:` fields. Dedup only within (Contract, function). Different function = different bug. Second pass above stays WITHIN (Contract, function), never across.\n\n   **MANDATORY — Fix preservation (HARD GATE).** Before writing merged `fix:` on a multi-finding (Contract, function):\n   1. Collect every raw `fix:` from agents flagging the tuple.\n   2. Group by ADD-lines (`+` lines, or equivalent require\u002Fassignment).\n   3. Distinct if ADD-lines differ in: called function\u002Fexpression (e.g., `require(msg.value == amount)` vs `require(zrc20 != _ETH_ADDRESS_)`), check direction (validate\u002Frestrict\u002Fban), or checked parameter.\n   4. ≥2 distinct → present as Option A, B, … — one block per distinct fix, verbatim from agent text (no paraphrase).\n   5. Label intuitively: validate \u002F restrict \u002F allow-and-handle \u002F ban-path.\n\n   **Output format when 2+ distinct fixes exist:**\n\n   ```\n   **Fix (Option A — \u003Clabel>)**:\n\n   ```diff\n   \u003Cverbatim diff from raw agent N1's fix>\n   ```\n\n   **Fix (Option B — \u003Clabel>)**:\n\n   ```diff\n   \u003Cverbatim diff from raw agent N2's fix>\n   ```\n   ```\n\n   **Inline check before printing**: count distinct fixes from raw for this (Contract, function). ≥2 distinct but merged shows 1 → violation, add alternatives.\n\n   **MANDATORY — Completeness (HARD GATE).** Before print: list every unique (Contract, function, bug-class) in any raw FINDING\u002FLEAD across the 12 agents. Every unique (Contract, function) MUST have ≥1 item in final. Zero = silent drop, fix it. Multiple bug-class within same (Contract, function) MAY collapse to one item (wide-description), but the (Contract, function) MUST survive. Print inline before report: `Completeness: N unique (Contract, function) in raw, N covered in final.`\n\n   Composite chains: if A's output feeds B's precondition AND combined impact > either alone, add `Chain: [A] + [B]` at conf = min(A, B). Most audits: 0–2.\n\n2. **Gate.** Run each deduped finding through the four gates in `judging.md` (no skip, no reorder, no revisit after verdict).\n\n   **Single-pass:** every relevant code path ONCE in fixed order (constructor → setters → swap → mint → burn → liquidate). One-line verdict: `BLOCKS` \u002F `ALLOWS` \u002F `IRRELEVANT` \u002F `UNCERTAIN`. `UNCERTAIN = ALLOWS`. Commit, no re-examination.\n\n3. **Lead promotion \u002F rejection.**\n   - LEAD → FINDING (conf 75) if: full exploit chain in source, OR `[agents: 2+]` demoted (not rejected) same issue.\n   - `[agents: 2+]` does NOT override a code path that interrupts attack before harm — demote to LEAD if execution uncertain.\n   - No deployer-intent reasoning — what code allows, not how deployer might use it.\n\n4. **Format\u002Fprint** per `report-formatting.md`. Exclude rejected. If `--file-output`: also write to file. Do NOT re-read source to \"verify the most critical claim\" — agents did that, dedup filtered. Re-verification costs ~5min, rarely changes verdicts. Skip.\n\n5. **Auto-clean.** After print (and `--file-output` write): `rm -rf {bundle_dir}`. Bundle dir = transient build state, not an artifact. Don't skip. For debugging: copy bundle elsewhere before re-running.\n\n\n## Banner\n\nBefore doing anything else, print this exactly:\n\n```\n\n██████╗  █████╗ ███████╗██╗  ██╗ ██████╗ ██╗   ██╗     ███████╗██╗  ██╗██╗██╗     ██╗     ███████╗\n██╔══██╗██╔══██╗██╔════╝██║  ██║██╔═══██╗██║   ██║     ██╔════╝██║ ██╔╝██║██║     ██║     ██╔════╝\n██████╔╝███████║███████╗███████║██║   ██║██║   ██║     ███████╗█████╔╝ ██║██║     ██║     ███████╗\n██╔═══╝ ██╔══██║╚════██║██╔══██║██║   ██║╚██╗ ██╔╝     ╚════██║██╔═██╗ ██║██║     ██║     ╚════██║\n██║     ██║  ██║███████║██║  ██║╚██████╔╝ ╚████╔╝      ███████║██║  ██╗██║███████╗███████╗███████║\n╚═╝     ╚═╝  ╚═╝╚══════╝╚═╝  ╚═╝ ╚═════╝   ╚═══╝       ╚══════╝╚═╝  ╚═╝╚═╝╚══════╝╚══════╝╚══════╝\n\n```\n",{"name":5,"description":7},"main","6b6406ecd922c4127bc688e0b5122bbe395be0eb","plugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor",6,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills","https:\u002F\u002Fgithub.com\u002Fwildcat-finance","https:\u002F\u002Fwildcat.finance","Banking, But Worse","2026-11-07 17:14:07",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add wildcat-finance\u002Fskills --skill solidity-auditor",{"tool":40,"command":41},"bunx","bunx skills add wildcat-finance\u002Fskills --skill solidity-auditor",{"tool":43,"command":44},"pnpm","pnpm dlx skills add wildcat-finance\u002Fskills --skill solidity-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002FSKILL.md",true,[48,54,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",251,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":16},"LICENSE","许可证",1079,{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"NOTICE.md",1178,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002FNOTICE.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fhacking-agents\u002Faccess-control-agent.md",1865,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Faccess-control-agent.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fhacking-agents\u002Fasymmetry-agent.md",4685,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fasymmetry-agent.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fhacking-agents\u002Fboundary-agent.md",6470,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fboundary-agent.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fhacking-agents\u002Feconomic-security-agent.md",2557,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Feconomic-security-agent.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fhacking-agents\u002Fexecution-trace-agent.md",2747,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fexecution-trace-agent.md",{"path":83,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fhacking-agents\u002Ffirst-principles-agent.md",2049,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Ffirst-principles-agent.md",{"path":87,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fhacking-agents\u002Fflow-gap-agent.md",5844,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fflow-gap-agent.md",{"path":91,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fhacking-agents\u002Finvariant-agent.md",4381,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Finvariant-agent.md",{"path":95,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fhacking-agents\u002Fmath-precision-agent.md",3884,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fmath-precision-agent.md",{"path":99,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fhacking-agents\u002Fnumerical-gap-agent.md",5179,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fnumerical-gap-agent.md",{"path":103,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fhacking-agents\u002Fperiphery-agent.md",3370,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fperiphery-agent.md",{"path":107,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fhacking-agents\u002Fshared-rules.md",4918,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Fshared-rules.md",{"path":111,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fhacking-agents\u002Ftrust-gap-agent.md",4011,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fhacking-agents\u002Ftrust-gap-agent.md",{"path":115,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fjudging.md",4275,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fjudging.md",{"path":119,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Freport-formatting.md",2827,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Freport-formatting.md",{"path":123,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fsenior-auditor-sop.md",4074,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002Freferences\u002Fsenior-auditor-sop.md",{"path":127,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":130,"sourceHtmlUrl":131},"VERSION","OTHER","其他",2,"https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fhexaemeron\u002Fskills\u002Fsolidity-auditor\u002FVERSION",[133,141,147,154,160,166],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":137,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":20},"01M7APAWXHFSKVQEJBAHKASH25","example","A deliberately unsupported evidence class fixture.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpromise-machine\u002Funsupported-evidence-class\u002Fplugins\u002Fexample\u002Fskills\u002Fexample\u002FSKILL.md",[],[],{"skillNo":142,"name":135,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":137,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":20},"01M7APATBK93107VF5NMPA3RJH","A router fixture target.","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpromise-machine\u002Funresolved-router\u002Fplugins\u002Fexample\u002Fskills\u002Fexample\u002FSKILL.md",[],[],{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":137,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":20},"01M7APARV9C0MQB8WTB0GGAAMG","promise-machine","A deliberately unresolved router.","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpromise-machine\u002Funresolved-router\u002F.agents\u002Fskills\u002Fpromise-machine\u002FSKILL.md",[],[],{"skillNo":155,"name":135,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":137,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":20},"01M7APAQMDG4977HXGSKMB29KV","A deliberately unclassified skill fixture.","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpromise-machine\u002Funclassified-skill\u002Fplugins\u002Fexample\u002Fskills\u002Fexample\u002FSKILL.md",[],[],{"skillNo":161,"name":135,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":137,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":20},"01M7APAPE6DE05A24J4BYPK6WY","A deliberately unattributed exception fixture.","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpromise-machine\u002Funattributed-exception\u002Fplugins\u002Fexample\u002Fskills\u002Fexample\u002FSKILL.md",[],[],{"skillNo":167,"name":135,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":137,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":20},"01M7APAKYXRTABBSN7Q637CC6M","A deliberately conflated version fixture.","https:\u002F\u002Fgithub.com\u002Fwildcat-finance\u002Fskills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpromise-machine\u002Fpackage-as-skill-version\u002Fplugins\u002Fexample\u002Fskills\u002Fexample\u002FSKILL.md",[],[]]