[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4T42ATCWYN78B5MH51QZX":3,"skill-same:01M7F4T42ATCWYN78B5MH51QZX":136},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7F4T42ATCWYN78B5MH51QZX","skill-creator",null,"Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: skill-creator\ndescription: \"Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.\"\nlicense: MIT\neffort: max\nmetadata:\n  version: 1.17.0\n  author: \"Luong NGUYEN \u003Cluongnv89@gmail.com>\"\n---\n\n# Skill Creator\n\nA skill for creating new skills and iteratively improving them. The agent's context budget is the primary constraint, so this SKILL.md links out to focused reference files.\n\nThe core loop:\n\n1. Decide what the skill should do and how it should do it\n2. Write a draft\n3. Run test prompts against claude-with-access-to-the-skill\n4. Evaluate results with the user (qualitative review via `eval-viewer\u002Fgenerate_review.py`, plus quantitative evals)\n5. Revise the skill based on feedback and benchmarks\n6. Repeat until satisfied; expand the test set and try again at scale\n\nIdentify where the user is in this loop and jump in there. New skill from scratch → start at step 1. Existing draft → jump to step 3 or 4. User wants to vibe-iterate without formal evals → support that. After the skill stabilizes, optionally run the description improver to optimize triggering.\n\n## Two entry paths\n\nThe skill supports two distinct workflows. **Identify which one the user is on before you do anything else** — they don't share a starting step.\n\n- **Path A — Create a new skill from scratch.** The user wants to capture a workflow, codify a pattern, or build a new capability. Start at **\"Creating a skill\"** below (Capture Intent → Interview → Write SKILL.md → Test → Eval).\n- **Path B — Improve an existing skill.** The user points to a skill that already exists and wants it brought up to standard, fixed, optimized, or iterated based on eval feedback. **Do not start with Capture Intent** — the intent is already encoded in the existing SKILL.md. Start at **\"Improving an existing skill\"** below.\n\nIf the request is ambiguous (\"can you look at this skill?\"), assume **Path B** and confirm before interviewing as if it were new. Path B also fires when `\u002Fskill-creator` is invoked on a skill directory or file.\n\nBoth paths share the mandatory rules below: **Repo Sync Before Edits**, **Dependency Preflight**, **Version Management**, **YAML Frontmatter Safety**, and **Frontmatter Audit on Review\u002FEvaluation**. Apply them in either path. Both paths also close with the **Run stats** block.\n\n## Step Completion Reports\n\nAfter completing each major step, output a status report in this format:\n\n```\n◆ [Step Name] ([step N of M] — [context])\n··································································\n  [Check 1]:          √ pass\n  [Check 2]:          √ pass (note if relevant)\n  [Check 3]:          × fail — [reason]\n  [Check 4]:          √ pass\n  [Criteria]:         √ N\u002FM met\n  ____________________________\n  Result:             PASS | FAIL | PARTIAL\n```\n\nAdapt the check names to match what the step actually validates. Use `√` for pass, `×` for fail, and `—` to add brief context. The \"Criteria\" line summarizes how many acceptance criteria were met. The \"Result\" line gives the overall verdict.\n\nPer-phase checks:\n\n| Phase          | Checks                                                                                                                            |\n| -------------- | --------------------------------------------------------------------------------------------------------------------------------- |\n| Intent Capture | `Worth building`, `Goal defined`, `Triggers identified`, `Output format agreed`                                                   |\n| Skill Writing  | `SKILL.md written`, `README generated`, `Subagents designed`, `Dependency preflight`, `Predictability pass`, `Adversarial review` |\n| Testing        | `Evals created`, `Runs completed`, `Viewer launched`                                                                              |\n| Iteration      | `Feedback incorporated`, `Benchmarks improved`, `Description optimized`                                                           |\n\n`Dependency preflight` is `√` when the skill has no skill dependencies, or has them and ships a gate for each; `×` when a dependency is invoked without one. `Predictability pass` walks the 7 rubric items from _Make it predictable_ — `√` per item satisfied, `×` naming the gap. `Adversarial review` is `√` once fresh-subagent findings are addressed.\n\n## Run stats (mandatory)\n\nEvery run that creates or updates a skill closes its summary with a run-stats block — the last thing printed, after the final Step Completion Report. It reports what the run **cost**, and nothing the run already reported.\n\nCapture `run_started_epoch` **once**, in the same shell as the skill's first command — `cmd; ec=$?; date +%s >&2; exit \"$ec\"` — reading the epoch off stderr so stdout and the exit code stay intact. Set it there, not later: without the anchor `elapsed` prints `n\u002Fa`, and the block still has to print on an early stop.\n\n```\n  ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄\n  Run stats   elapsed 6m 04s · tokens 128,400 · cost $0.42\n              agents 3 · skills 1 · tool calls 47\n```\n\nFields are fixed and in this order — never reordered, renamed, or added to: `elapsed`, `tokens`, `cost`, `agents`, `skills`, `tool calls`. Per-field formatting: `references\u002Frun-stats.md`.\n\n- **`tokens` and `cost` are omitted entirely when the host reported no figure** — no dangling `·`, no placeholder. Never estimate one, and never reconstruct one from host transcripts or logs.\n- **`elapsed`, `agents`, `skills`, and `tool calls` always print.** A value that cannot be determined prints the literal `n\u002Fa`; `0` is a determined value and is correct where it is true (a run that spawned no subagents prints `agents 0`).\n- A missing optional figure never suppresses the rest of the block.\n\nPrint it on **every** path that finishes a create or update — Path A, Subpath B1, and Subpath B2 — and on every other terminal outcome too: an early stop, a gate that refused to continue, or a failed step. Only a run that produced no output at all has no block.\n\n## Communicating with the user\n\nUsers span a wide range of technical familiarity. Match jargon to context cues — terms like \"JSON\" or \"assertion\" need evidence the user knows them; briefly define terms when in doubt.\n\n---\n\n## Mandatory Rule for Repo-Mutating Skills\n\nWhen creating or updating any skill that changes files in a git repository (code, docs, config, commits, publishing), include this rule in that skill's SKILL.md:\n\n- Add a **\"Repo Sync Before Edits (mandatory)\"** section near the top requiring `branch=\"$(git rev-parse --abbrev-ref HEAD)\"; git fetch origin && git pull --rebase origin \"$branch\"` before modifications.\n- If the working tree is dirty: stash, sync, then pop.\n- If `origin` is missing or conflicts occur: stop and ask the user before continuing.\n\nDo not ship repo-mutating skills without this pre-sync guardrail.\n\n## Mandatory Rule for Skills That Invoke Other Skills\n\nEstablish, for every skill you author or retrofit, whether it invokes, delegates to, or reads **another skill**. Ask it in the interview — _Does this skill invoke other skills?_ is Capture Intent question 6 — and confirm the answer against the draft: prose naming `\u002Fanother-skill`, or a read under `~\u002F.claude\u002Fskills\u002F`, is a dependency even when the author said there were none.\n\n- **It does** → declare each optional dependency in the frontmatter `dependencies` list and ship a `## Dependency Preflight (mandatory)` section above the first step that changes anything. The main agent acquires only a dependency whose branch it reaches with `asm deps acquire ... --session \u003Ccaller-session-id>`, uses the returned path directly, and releases the session in caller-owned `finally`\u002Fshutdown handling.\n- **It does not** → add nothing. No empty preflight section, no \"no dependencies\" placeholder.\n\nRead `references\u002Fdependency-preflight.md` for the copyable template and the on-miss behavior. `skill-auto-improver` audits for this same rule, so a skill that ships without a required gate comes back as a finding later.\n\n## Frontmatter rules (mandatory)\n\nRead `references\u002Ffrontmatter-rules.md` for the full mandatory rules:\n\n- **Version Management** — set `metadata.version: 1.0.0` on creation; bump patch\u002Fminor\u002Fmajor on every edit.\n- **YAML Frontmatter Safety** — double-quote any string value containing YAML-special characters (full list in the reference).\n- **Frontmatter Audit on Review\u002FEvaluation** — required-field check, name\u002Fdir match, allowed top-level keys, `metadata.version`, `metadata.author`, YAML safety, and consistency with `docs\u002FREADME.md`. Run `python scripts\u002Fquick_validate.py \u003Cskill-path>` first; it catches mechanical issues without LLM reasoning.\n\nThese rules apply on every write. Always confirm them before saving.\n\n## Creating a skill\n\n### Capture Intent\n\nRead `references\u002Fintent-interview.md` and work it top to bottom. It carries:\n\n- **The gate** — a skill earns its place only when the workflow is repeated, non-obvious, and stable. Recommend against creating it otherwise; the user can override.\n- **The seven interview questions** — purpose, triggers, the expected output format, test cases, subagents (including per-step context delegation), skill dependencies, and model-invoked vs. user-invoked (`\u002Fskill-name` is orchestration the user runs deliberately — a pipeline, or an expensive or destructive action they confirm first).\n- **Interview and research** — edge cases, example files, success criteria, available MCPs.\n- **Branch mapping before drafting** — name the distinct modes the skill runs in, so branch-specific material is disclosed only on the branch that uses it.\n\nExtract what the conversation already answers before asking the user anything; they fill the gaps and confirm.\n\n### Write the SKILL.md\n\nBefore drafting, skim `references\u002Fexemplars.md` and imitate the archetype closest to this skill — workflow, knowledge, or orchestrator. Then, based on the user interview, fill in:\n\n- **name**: 1-64 chars, lowercase letters\u002Fdigits\u002Fhyphens, no consecutive hyphens, exactly matches parent directory. Enforced by `scripts\u002Fquick_validate.py`.\n- **description**: When to trigger and what it does. Primary triggering mechanism. Single line, no newlines. Claude tends to _undertrigger_ — make descriptions a little \"pushy\", with negative triggers.\n- **effort** (optional): `low | medium | high | xhigh | max`. Defaults to `high`.\n- **metadata.version**: Semver string (see frontmatter rules).\n- **compatibility**: Required tools or dependencies (rare).\n\n#### Writing a good description\n\nRead `references\u002Fdescription-guide.md` for the full guide: the pushy + negative-triggers pattern (a \"Don't use for ...\" clause naming 2–3 adjacent domains), one trigger per branch, and the three length limits. The rule that bites first: **target ≤250 characters** — Claude Code's `\u002Fskills` listing truncates tail-first beyond that, chopping the negative-trigger clause. `scripts\u002Fquick_validate.py` warns (non-fatal) when the negative clause looks missing.\n\n### Skill Writing Guide\n\nRead `references\u002Fwriting-guide.md` for the full guide. It covers anatomy (where `agents\u002F`, `references\u002F`, `scripts\u002F`, `assets\u002F`, `docs\u002F` go), progressive disclosure and the 500-line SKILL.md cap, the Principle of Lack of Surprise, writing and workflow patterns, bundled-script error messages, Step Completion Reports, writing style, `docs\u002FREADME.md` generation (`references\u002Freadme-template.md`), the 5-prompt test-case floor saved to `evals\u002Fevals.json` (`references\u002Fschemas.md`), and the pre-eval LLM validation phases (`references\u002Fvalidation-prompts.md`).\n\n### Make it predictable (publish-ready by construction)\n\nThe goal of creating a skill here is a **predictable process** — the agent follows the same reliable path every run — and a skill that ships **publish-ready** without later needing a `skill-auto-improver` cleanup pass. Read `references\u002Fpredictability-rubric.md` for the full standard and its checkable pass\u002Ffail bar. The hooks you apply _while writing_:\n\n- **Demanding completion criteria.** End every major step with a bar the agent can _check_, not vibe — tied to a command, file state, or count. The Step Completion Reports format above is the vehicle. Strong criteria are what stop the agent declaring success early.\n- **Progressive disclosure for non-universal material.** Anything branch-specific, long, or not needed on every run goes to `references\u002F` behind a one-line pointer — this keeps context load low and SKILL.md under the caps. Its step-level analogue is **per-step context delegation**: a delegable step names the slice of `references\u002F` its worker needs and hands that slice over as the worker's `Input`, so the main agent never holds the whole tree (`references\u002Fsubagent-patterns.md` → _Per-Step Context Delegation_, which also says when the slice isn't worth taking).\n- **Leading words.** Name a recurring concept once with a short load-bearing term (\"atomic commit\", \"fail-soft\", \"publish-ready\") and reuse the term, rather than re-explaining it at each use.\n- **Pruning pass — run before finishing.** One explicit pass to cut duplication, stale sediment, sprawl, and no-op instructions (\"be careful\", \"use good judgment\"). This pass is what most often separates a skill-creator-authored skill from one that still needs `skill-auto-improver`.\n\nBefore finishing, **walk all 7 rubric items** (the four hooks above plus invocation choice, branch mapping, and publish-ready) and emit the result as the `Predictability pass` row of the Skill Writing Step Completion Report. This makes the rubric walk visible instead of silent — a `×` is a fix-before-publish signal, not a blocker.\n\n`skill-auto-improver` remains the remediation tool for _externally authored_ or _legacy_ skills — not a required second stage for a skill created through this path.\n\n### Adversarial review (mandatory before evals)\n\nThe drafting context cannot review its own draft — it fills every gap from memory instead of from the page. After the rubric walk, spawn a **fresh subagent** with the draft skill and phases 1–3 of `references\u002Fvalidation-prompts.md` (discovery, logic walk, edge-case attack); it returns trigger misses, ambiguous steps, and breaking prompts. Fix the real findings before running evals; carry the rest into the test set. If no Agent tool is available, run the phases yourself in a fresh session (see `references\u002Fenvironment-modes.md`).\n\n## Running and evaluating test cases\n\nRead `references\u002Feval-loop.md` for the full 5-step sequence (spawn runs, draft assertions, capture timing, grade\u002Faggregate\u002Fview, read feedback). It covers the with-skill + baseline subagent pattern, the `eval_metadata.json` and `timing.json` formats, the `generate_review.py` invocation, and reading `feedback.json`.\n\nDo NOT use `\u002Fskill-test` or any other testing skill — the flow in `references\u002Feval-loop.md` is the one this skill expects.\n\n## Improving an existing skill\n\nThis is **Path B** from the entry-paths block at the top. Read `references\u002Fimproving-existing.md` and pick the subpath from what the user is asking for — they don't share an opening move.\n\n- **Subpath B1 — retrofit to the standard.** \"Update this skill to match the standard,\" \"fix this skill,\" \"review and improve.\" Mechanical conformance, not behavioral redesign: read the directory, run `quick_validate.py`, run the Frontmatter Audit, inspect the body against the standards above, fix or report, bump `metadata.version`, re-validate. **Do not interview the user about purpose, triggers, or output format** — those are already encoded in the SKILL.md. No evals required.\n- **Subpath B2 — iterate on eval feedback.** The user has eval results or wants to run them. The opening move is the **eval loop**, not interviewing: `evals\u002Fmisfires.jsonl` first, then results and `feedback.json`, revise per `references\u002Fiteration.md`, audit frontmatter alongside, bump the version, re-run evals into a new `iteration-\u003CN+1>\u002F` directory.\n\n## Description Optimization\n\nThe description field is the primary mechanism that determines whether Claude invokes a skill. After creating or improving a skill, offer to optimize the description for better triggering accuracy.\n\nRead `references\u002Fdescription-optimization.md` for the full 4-step flow: generate trigger eval queries, review with the user via the HTML template, run the optimization loop with `run_loop.py`, apply the best description.\n\n### Package and Present (only if `present_files` tool is available)\n\nIf the `present_files` tool is available (otherwise skip), package the skill and present the resulting `.skill` file path so the user can install it:\n\n```bash\npython -m scripts.package_skill \u003Cpath\u002Fto\u002Fskill-folder>\n```\n\n## Environment-specific notes\n\nIf you're on Claude.ai (no subagents) or in Cowork (subagents but no browser), some mechanics change. Read `references\u002Fenvironment-modes.md` for the adapted flow. The core loop (draft → test → review → improve) is the same everywhere — only execution mechanics shift.\n\n---\n\n## Reference files\n\n`agents\u002F` holds instructions for specialized subagents — read one when you spawn that subagent:\n\n- `agents\u002Fgrader.md` — evaluate assertions against outputs\n- `agents\u002Fcomparator.md` — blind A\u002FB comparison between two outputs\n- `agents\u002Fanalyzer.md` — analyze why one version beat another\n\n`references\u002F` holds the material this SKILL.md links out to:\n\n| File                          | Contents                                                                                      |\n| ----------------------------- | --------------------------------------------------------------------------------------------- |\n| `frontmatter-rules.md`        | Version Management, YAML Safety, Frontmatter Audit (mandatory)                                |\n| `dependency-preflight.md`     | When a preflight gate is required, what it names, and the template to emit (mandatory)        |\n| `predictability-rubric.md`    | The 7-item predictability standard a new skill must meet by construction                      |\n| `intent-interview.md`         | Path A opening: the should-this-exist gate, the 7 questions, research, branch mapping         |\n| `improving-existing.md`       | Path B: the Subpath B1 retrofit sequence and the Subpath B2 eval-feedback sequence            |\n| `description-guide.md`        | Pushy + negative-trigger description pattern, one trigger per branch, length budget           |\n| `exemplars.md`                | Three annotated exemplar skills (workflow, knowledge, orchestrator) to imitate                |\n| `writing-guide.md`            | Anatomy, progressive disclosure, writing and workflow patterns, error messages, test cases    |\n| `schemas.md`                  | JSON structures for `evals.json`, `misfires.jsonl`, `grading.json`, etc.                      |\n| `subagent-patterns.md`        | When and how to use the Agent tool, including per-step context delegation and when to skip it |\n| `validation-prompts.md`       | The 4 validation phases; 1–3 script the mandatory adversarial review                          |\n| `eval-loop.md`                | Full 5-step eval run \u002F grade \u002F viewer flow                                                    |\n| `iteration.md`                | Principles for improving a skill based on feedback; blind comparison                          |\n| `description-optimization.md` | 4-step description-tuning workflow                                                            |\n| `environment-modes.md`        | Claude.ai and Cowork-specific adaptations                                                     |\n| `readme-template.md`          | AI-skip notice, template, and rules for `docs\u002FREADME.md`                                      |\n| `run-stats.md`                | Run-stats field definitions and the start-epoch capture command                               |\n\n---\n\nIn any task list, include \"Create evals JSON and run `eval-viewer\u002Fgenerate_review.py` for human review\" — especially in Cowork, where it's easy to skip.\n","# Skill Creator\n\nA skill for creating new skills and iteratively improving them. The agent's context budget is the primary constraint, so this SKILL.md links out to focused reference files.\n\nThe core loop:\n\n1. Decide what the skill should do and how it should do it\n2. Write a draft\n3. Run test prompts against claude-with-access-to-the-skill\n4. Evaluate results with the user (qualitative review via `eval-viewer\u002Fgenerate_review.py`, plus quantitative evals)\n5. Revise the skill based on feedback and benchmarks\n6. Repeat until satisfied; expand the test set and try again at scale\n\nIdentify where the user is in this loop and jump in there. New skill from scratch → start at step 1. Existing draft → jump to step 3 or 4. User wants to vibe-iterate without formal evals → support that. After the skill stabilizes, optionally run the description improver to optimize triggering.\n\n## Two entry paths\n\nThe skill supports two distinct workflows. **Identify which one the user is on before you do anything else** — they don't share a starting step.\n\n- **Path A — Create a new skill from scratch.** The user wants to capture a workflow, codify a pattern, or build a new capability. Start at **\"Creating a skill\"** below (Capture Intent → Interview → Write SKILL.md → Test → Eval).\n- **Path B — Improve an existing skill.** The user points to a skill that already exists and wants it brought up to standard, fixed, optimized, or iterated based on eval feedback. **Do not start with Capture Intent** — the intent is already encoded in the existing SKILL.md. Start at **\"Improving an existing skill\"** below.\n\nIf the request is ambiguous (\"can you look at this skill?\"), assume **Path B** and confirm before interviewing as if it were new. Path B also fires when `\u002Fskill-creator` is invoked on a skill directory or file.\n\nBoth paths share the mandatory rules below: **Repo Sync Before Edits**, **Dependency Preflight**, **Version Management**, **YAML Frontmatter Safety**, and **Frontmatter Audit on Review\u002FEvaluation**. Apply them in either path. Both paths also close with the **Run stats** block.\n\n## Step Completion Reports\n\nAfter completing each major step, output a status report in this format:\n\n```\n◆ [Step Name] ([step N of M] — [context])\n··································································\n  [Check 1]:          √ pass\n  [Check 2]:          √ pass (note if relevant)\n  [Check 3]:          × fail — [reason]\n  [Check 4]:          √ pass\n  [Criteria]:         √ N\u002FM met\n  ____________________________\n  Result:             PASS | FAIL | PARTIAL\n```\n\nAdapt the check names to match what the step actually validates. Use `√` for pass, `×` for fail, and `—` to add brief context. The \"Criteria\" line summarizes how many acceptance criteria were met. The \"Result\" line gives the overall verdict.\n\nPer-phase checks:\n\n| Phase          | Checks                                                                                                                            |\n| -------------- | --------------------------------------------------------------------------------------------------------------------------------- |\n| Intent Capture | `Worth building`, `Goal defined`, `Triggers identified`, `Output format agreed`                                                   |\n| Skill Writing  | `SKILL.md written`, `README generated`, `Subagents designed`, `Dependency preflight`, `Predictability pass`, `Adversarial review` |\n| Testing        | `Evals created`, `Runs completed`, `Viewer launched`                                                                              |\n| Iteration      | `Feedback incorporated`, `Benchmarks improved`, `Description optimized`                                                           |\n\n`Dependency preflight` is `√` when the skill has no skill dependencies, or has them and ships a gate for each; `×` when a dependency is invoked without one. `Predictability pass` walks the 7 rubric items from _Make it predictable_ — `√` per item satisfied, `×` naming the gap. `Adversarial review` is `√` once fresh-subagent findings are addressed.\n\n## Run stats (mandatory)\n\nEvery run that creates or updates a skill closes its summary with a run-stats block — the last thing printed, after the final Step Completion Report. It reports what the run **cost**, and nothing the run already reported.\n\nCapture `run_started_epoch` **once**, in the same shell as the skill's first command — `cmd; ec=$?; date +%s >&2; exit \"$ec\"` — reading the epoch off stderr so stdout and the exit code stay intact. Set it there, not later: without the anchor `elapsed` prints `n\u002Fa`, and the block still has to print on an early stop.\n\n```\n  ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄\n  Run stats   elapsed 6m 04s · tokens 128,400 · cost $0.42\n              agents 3 · skills 1 · tool calls 47\n```\n\nFields are fixed and in this order — never reordered, renamed, or added to: `elapsed`, `tokens`, `cost`, `agents`, `skills`, `tool calls`. Per-field formatting: `references\u002Frun-stats.md`.\n\n- **`tokens` and `cost` are omitted entirely when the host reported no figure** — no dangling `·`, no placeholder. Never estimate one, and never reconstruct one from host transcripts or logs.\n- **`elapsed`, `agents`, `skills`, and `tool calls` always print.** A value that cannot be determined prints the literal `n\u002Fa`; `0` is a determined value and is correct where it is true (a run that spawned no subagents prints `agents 0`).\n- A missing optional figure never suppresses the rest of the block.\n\nPrint it on **every** path that finishes a create or update — Path A, Subpath B1, and Subpath B2 — and on every other terminal outcome too: an early stop, a gate that refused to continue, or a failed step. Only a run that produced no output at all has no block.\n\n## Communicating with the user\n\nUsers span a wide range of technical familiarity. Match jargon to context cues — terms like \"JSON\" or \"assertion\" need evidence the user knows them; briefly define terms when in doubt.\n\n---\n\n## Mandatory Rule for Repo-Mutating Skills\n\nWhen creating or updating any skill that changes files in a git repository (code, docs, config, commits, publishing), include this rule in that skill's SKILL.md:\n\n- Add a **\"Repo Sync Before Edits (mandatory)\"** section near the top requiring `branch=\"$(git rev-parse --abbrev-ref HEAD)\"; git fetch origin && git pull --rebase origin \"$branch\"` before modifications.\n- If the working tree is dirty: stash, sync, then pop.\n- If `origin` is missing or conflicts occur: stop and ask the user before continuing.\n\nDo not ship repo-mutating skills without this pre-sync guardrail.\n\n## Mandatory Rule for Skills That Invoke Other Skills\n\nEstablish, for every skill you author or retrofit, whether it invokes, delegates to, or reads **another skill**. Ask it in the interview — _Does this skill invoke other skills?_ is Capture Intent question 6 — and confirm the answer against the draft: prose naming `\u002Fanother-skill`, or a read under `~\u002F.claude\u002Fskills\u002F`, is a dependency even when the author said there were none.\n\n- **It does** → declare each optional dependency in the frontmatter `dependencies` list and ship a `## Dependency Preflight (mandatory)` section above the first step that changes anything. The main agent acquires only a dependency whose branch it reaches with `asm deps acquire ... --session \u003Ccaller-session-id>`, uses the returned path directly, and releases the session in caller-owned `finally`\u002Fshutdown handling.\n- **It does not** → add nothing. No empty preflight section, no \"no dependencies\" placeholder.\n\nRead `references\u002Fdependency-preflight.md` for the copyable template and the on-miss behavior. `skill-auto-improver` audits for this same rule, so a skill that ships without a required gate comes back as a finding later.\n\n## Frontmatter rules (mandatory)\n\nRead `references\u002Ffrontmatter-rules.md` for the full mandatory rules:\n\n- **Version Management** — set `metadata.version: 1.0.0` on creation; bump patch\u002Fminor\u002Fmajor on every edit.\n- **YAML Frontmatter Safety** — double-quote any string value containing YAML-special characters (full list in the reference).\n- **Frontmatter Audit on Review\u002FEvaluation** — required-field check, name\u002Fdir match, allowed top-level keys, `metadata.version`, `metadata.author`, YAML safety, and consistency with `docs\u002FREADME.md`. Run `python scripts\u002Fquick_validate.py \u003Cskill-path>` first; it catches mechanical issues without LLM reasoning.\n\nThese rules apply on every write. Always confirm them before saving.\n\n## Creating a skill\n\n### Capture Intent\n\nRead `references\u002Fintent-interview.md` and work it top to bottom. It carries:\n\n- **The gate** — a skill earns its place only when the workflow is repeated, non-obvious, and stable. Recommend against creating it otherwise; the user can override.\n- **The seven interview questions** — purpose, triggers, the expected output format, test cases, subagents (including per-step context delegation), skill dependencies, and model-invoked vs. user-invoked (`\u002Fskill-name` is orchestration the user runs deliberately — a pipeline, or an expensive or destructive action they confirm first).\n- **Interview and research** — edge cases, example files, success criteria, available MCPs.\n- **Branch mapping before drafting** — name the distinct modes the skill runs in, so branch-specific material is disclosed only on the branch that uses it.\n\nExtract what the conversation already answers before asking the user anything; they fill the gaps and confirm.\n\n### Write the SKILL.md\n\nBefore drafting, skim `references\u002Fexemplars.md` and imitate the archetype closest to this skill — workflow, knowledge, or orchestrator. Then, based on the user interview, fill in:\n\n- **name**: 1-64 chars, lowercase letters\u002Fdigits\u002Fhyphens, no consecutive hyphens, exactly matches parent directory. Enforced by `scripts\u002Fquick_validate.py`.\n- **description**: When to trigger and what it does. Primary triggering mechanism. Single line, no newlines. Claude tends to _undertrigger_ — make descriptions a little \"pushy\", with negative triggers.\n- **effort** (optional): `low | medium | high | xhigh | max`. Defaults to `high`.\n- **metadata.version**: Semver string (see frontmatter rules).\n- **compatibility**: Required tools or dependencies (rare).\n\n#### Writing a good description\n\nRead `references\u002Fdescription-guide.md` for the full guide: the pushy + negative-triggers pattern (a \"Don't use for ...\" clause naming 2–3 adjacent domains), one trigger per branch, and the three length limits. The rule that bites first: **target ≤250 characters** — Claude Code's `\u002Fskills` listing truncates tail-first beyond that, chopping the negative-trigger clause. `scripts\u002Fquick_validate.py` warns (non-fatal) when the negative clause looks missing.\n\n### Skill Writing Guide\n\nRead `references\u002Fwriting-guide.md` for the full guide. It covers anatomy (where `agents\u002F`, `references\u002F`, `scripts\u002F`, `assets\u002F`, `docs\u002F` go), progressive disclosure and the 500-line SKILL.md cap, the Principle of Lack of Surprise, writing and workflow patterns, bundled-script error messages, Step Completion Reports, writing style, `docs\u002FREADME.md` generation (`references\u002Freadme-template.md`), the 5-prompt test-case floor saved to `evals\u002Fevals.json` (`references\u002Fschemas.md`), and the pre-eval LLM validation phases (`references\u002Fvalidation-prompts.md`).\n\n### Make it predictable (publish-ready by construction)\n\nThe goal of creating a skill here is a **predictable process** — the agent follows the same reliable path every run — and a skill that ships **publish-ready** without later needing a `skill-auto-improver` cleanup pass. Read `references\u002Fpredictability-rubric.md` for the full standard and its checkable pass\u002Ffail bar. The hooks you apply _while writing_:\n\n- **Demanding completion criteria.** End every major step with a bar the agent can _check_, not vibe — tied to a command, file state, or count. The Step Completion Reports format above is the vehicle. Strong criteria are what stop the agent declaring success early.\n- **Progressive disclosure for non-universal material.** Anything branch-specific, long, or not needed on every run goes to `references\u002F` behind a one-line pointer — this keeps context load low and SKILL.md under the caps. Its step-level analogue is **per-step context delegation**: a delegable step names the slice of `references\u002F` its worker needs and hands that slice over as the worker's `Input`, so the main agent never holds the whole tree (`references\u002Fsubagent-patterns.md` → _Per-Step Context Delegation_, which also says when the slice isn't worth taking).\n- **Leading words.** Name a recurring concept once with a short load-bearing term (\"atomic commit\", \"fail-soft\", \"publish-ready\") and reuse the term, rather than re-explaining it at each use.\n- **Pruning pass — run before finishing.** One explicit pass to cut duplication, stale sediment, sprawl, and no-op instructions (\"be careful\", \"use good judgment\"). This pass is what most often separates a skill-creator-authored skill from one that still needs `skill-auto-improver`.\n\nBefore finishing, **walk all 7 rubric items** (the four hooks above plus invocation choice, branch mapping, and publish-ready) and emit the result as the `Predictability pass` row of the Skill Writing Step Completion Report. This makes the rubric walk visible instead of silent — a `×` is a fix-before-publish signal, not a blocker.\n\n`skill-auto-improver` remains the remediation tool for _externally authored_ or _legacy_ skills — not a required second stage for a skill created through this path.\n\n### Adversarial review (mandatory before evals)\n\nThe drafting context cannot review its own draft — it fills every gap from memory instead of from the page. After the rubric walk, spawn a **fresh subagent** with the draft skill and phases 1–3 of `references\u002Fvalidation-prompts.md` (discovery, logic walk, edge-case attack); it returns trigger misses, ambiguous steps, and breaking prompts. Fix the real findings before running evals; carry the rest into the test set. If no Agent tool is available, run the phases yourself in a fresh session (see `references\u002Fenvironment-modes.md`).\n\n## Running and evaluating test cases\n\nRead `references\u002Feval-loop.md` for the full 5-step sequence (spawn runs, draft assertions, capture timing, grade\u002Faggregate\u002Fview, read feedback). It covers the with-skill + baseline subagent pattern, the `eval_metadata.json` and `timing.json` formats, the `generate_review.py` invocation, and reading `feedback.json`.\n\nDo NOT use `\u002Fskill-test` or any other testing skill — the flow in `references\u002Feval-loop.md` is the one this skill expects.\n\n## Improving an existing skill\n\nThis is **Path B** from the entry-paths block at the top. Read `references\u002Fimproving-existing.md` and pick the subpath from what the user is asking for — they don't share an opening move.\n\n- **Subpath B1 — retrofit to the standard.** \"Update this skill to match the standard,\" \"fix this skill,\" \"review and improve.\" Mechanical conformance, not behavioral redesign: read the directory, run `quick_validate.py`, run the Frontmatter Audit, inspect the body against the standards above, fix or report, bump `metadata.version`, re-validate. **Do not interview the user about purpose, triggers, or output format** — those are already encoded in the SKILL.md. No evals required.\n- **Subpath B2 — iterate on eval feedback.** The user has eval results or wants to run them. The opening move is the **eval loop**, not interviewing: `evals\u002Fmisfires.jsonl` first, then results and `feedback.json`, revise per `references\u002Fiteration.md`, audit frontmatter alongside, bump the version, re-run evals into a new `iteration-\u003CN+1>\u002F` directory.\n\n## Description Optimization\n\nThe description field is the primary mechanism that determines whether Claude invokes a skill. After creating or improving a skill, offer to optimize the description for better triggering accuracy.\n\nRead `references\u002Fdescription-optimization.md` for the full 4-step flow: generate trigger eval queries, review with the user via the HTML template, run the optimization loop with `run_loop.py`, apply the best description.\n\n### Package and Present (only if `present_files` tool is available)\n\nIf the `present_files` tool is available (otherwise skip), package the skill and present the resulting `.skill` file path so the user can install it:\n\n```bash\npython -m scripts.package_skill \u003Cpath\u002Fto\u002Fskill-folder>\n```\n\n## Environment-specific notes\n\nIf you're on Claude.ai (no subagents) or in Cowork (subagents but no browser), some mechanics change. Read `references\u002Fenvironment-modes.md` for the adapted flow. The core loop (draft → test → review → improve) is the same everywhere — only execution mechanics shift.\n\n---\n\n## Reference files\n\n`agents\u002F` holds instructions for specialized subagents — read one when you spawn that subagent:\n\n- `agents\u002Fgrader.md` — evaluate assertions against outputs\n- `agents\u002Fcomparator.md` — blind A\u002FB comparison between two outputs\n- `agents\u002Fanalyzer.md` — analyze why one version beat another\n\n`references\u002F` holds the material this SKILL.md links out to:\n\n| File                          | Contents                                                                                      |\n| ----------------------------- | --------------------------------------------------------------------------------------------- |\n| `frontmatter-rules.md`        | Version Management, YAML Safety, Frontmatter Audit (mandatory)                                |\n| `dependency-preflight.md`     | When a preflight gate is required, what it names, and the template to emit (mandatory)        |\n| `predictability-rubric.md`    | The 7-item predictability standard a new skill must meet by construction                      |\n| `intent-interview.md`         | Path A opening: the should-this-exist gate, the 7 questions, research, branch mapping         |\n| `improving-existing.md`       | Path B: the Subpath B1 retrofit sequence and the Subpath B2 eval-feedback sequence            |\n| `description-guide.md`        | Pushy + negative-trigger description pattern, one trigger per branch, length budget           |\n| `exemplars.md`                | Three annotated exemplar skills (workflow, knowledge, orchestrator) to imitate                |\n| `writing-guide.md`            | Anatomy, progressive disclosure, writing and workflow patterns, error messages, test cases    |\n| `schemas.md`                  | JSON structures for `evals.json`, `misfires.jsonl`, `grading.json`, etc.                      |\n| `subagent-patterns.md`        | When and how to use the Agent tool, including per-step context delegation and when to skip it |\n| `validation-prompts.md`       | The 4 validation phases; 1–3 script the mandatory adversarial review                          |\n| `eval-loop.md`                | Full 5-step eval run \u002F grade \u002F viewer flow                                                    |\n| `iteration.md`                | Principles for improving a skill based on feedback; blind comparison                          |\n| `description-optimization.md` | 4-step description-tuning workflow                                                            |\n| `environment-modes.md`        | Claude.ai and Cowork-specific adaptations                                                     |\n| `readme-template.md`          | AI-skip notice, template, and rules for `docs\u002FREADME.md`                                      |\n| `run-stats.md`                | Run-stats field definitions and the start-epoch capture command                               |\n\n---\n\nIn any task list, include \"Create evals JSON and run `eval-viewer\u002Fgenerate_review.py` for human review\" — especially in Cowork, where it's easy to skip.\n",{"name":5,"effort":24,"license":15,"metadata":25,"description":7},"max",{"author":26,"version":27},"Luong NGUYEN \u003Cluongnv89@gmail.com>","1.17.0","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fskill-creator-luongnv89__asm",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-creator",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-creator",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002FSKILL.md",true,[50,56,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124,128,132],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"agents\u002Fanalyzer.md","REFERENCE","参考文档",10545,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Fagents\u002Fanalyzer.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"agents\u002Fcomparator.md",7567,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Fagents\u002Fcomparator.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002Fgrader.md",9053,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Fagents\u002Fgrader.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"docs\u002FREADME.md",4317,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Fdocs\u002FREADME.md",{"path":69,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fdependency-preflight.md",4604,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fdependency-preflight.md",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fdescription-guide.md",2676,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fdescription-guide.md",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fdescription-optimization.md",5645,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fdescription-optimization.md",{"path":81,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fenvironment-modes.md",4463,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fenvironment-modes.md",{"path":85,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Feval-loop.md",8976,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Feval-loop.md",{"path":89,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fexemplars.md",13332,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fexemplars.md",{"path":93,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Ffrontmatter-rules.md",5884,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Ffrontmatter-rules.md",{"path":97,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fimproving-existing.md",3462,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fimproving-existing.md",{"path":101,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fintent-interview.md",4311,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fintent-interview.md",{"path":105,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fiteration.md",6671,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fiteration.md",{"path":109,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fpredictability-rubric.md",10483,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fpredictability-rubric.md",{"path":113,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Freadme-template.md",3547,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Freadme-template.md",{"path":117,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Frun-stats.md",2065,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Frun-stats.md",{"path":121,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fschemas.md",14503,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fschemas.md",{"path":125,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fsubagent-patterns.md",20857,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fsubagent-patterns.md",{"path":129,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fvalidation-prompts.md",6887,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fvalidation-prompts.md",{"path":133,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fwriting-guide.md",12427,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-creator-luongnv89__asm\u002Freferences\u002Fwriting-guide.md",[137,144,149,156,163,170],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":145,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]