菜单
Creates and validates a skill's sample sets and eval sets (golden examples, anti-examples, and triggering cases) and detects drift against current behavior. Use when generating samples for a skill, building an eval set, or checking samples for drift.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Creates and improves agentskills.io skills to the Advanced Skill Library Standard. Use when you need to author a new SKILL.md, scaffold a skill directory, or raise an existing skill's conformance and description quality.
Evaluates a skill or plugin against the Advanced Skill Library Standard across three modes, producing deterministic conformance findings and a tier, an opt-in behavioral pass, and a qualitative review. Use when you want to audit conformance, judge whether a skill behaves and triggers correctly, get a qualitative review, or see what blocks the next tier.
Converts a meeting transcript into a decision log. Use when the user asks to extract decisions, action items, or owners from a transcript.
Assesses an existing skills repository against the Advanced Skill Library Standard, produces a staged bring-to-conformance plan, and writes the minimal canonical manifest so the repo becomes gradeable. Use when adopting a foreign or ad-hoc skills repo, migrating a Claude-only plugin toward cross-agent conformance, or planning a Bronze-to-Silver upgrade path.
Builds and validates a plugin's release by computing the version, promoting the changelog, curating the release notes, and running the readiness gate, to the Advanced Skill Library Standard. Use when cutting a release, bumping the plugin version, updating the changelog or release notes, or checking release readiness.
Creates, triages, and prunes a plugin's two backlogs (new-component proposals and enhancements) to the Advanced Skill Library Standard. Use when capturing a new-component proposal through the why-gate, prioritizing backlog items, or removing stale or completed entries.
| name | askit-build-samples |
| description | Creates and validates a skill's sample sets and eval sets (golden examples, anti-examples, and triggering cases) and detects drift against current behavior. Use when generating samples for a skill, building an eval set, or checking samples for drift. |
| metadata | {"version":"0.1.0","tier":"universal","audience":"advanced"} |
Author and validate the evidence a skill carries, following the builder pattern (../../docs/reference/builder-pattern.md). create generates a skill's samples (at least 3 golden examples plus at least 1 anti-example, Standard sec 7.2) under examples/, and its triggering eval set (at least 20 {query, should_trigger} cases, sec 8.3) plus any chain/hook behavior cases under evals/ in the eval-set format the G3 library-regression check and the askit-evaluate behavioral mode consume. validate detects drift: a sample or eval that no longer matches the skill's current behavior is an error, not a silent staleness. Format and the example-threads convention are in references/samples-format.md.
When generating samples or an eval set for a skill, or checking existing samples and evals for drift after a behavior change.
examples/ golden samples (>= 3 realistic input/output pairs) and an anti-example (>= 1 case the skill should NOT handle), per sec 7.2.evals/<name>.eval.json: a triggering set of >= 20 {query, should_trigger} cases (fires when it should, silent when it should not, sec 8.3), plus {given, expect} behavior cases for any chain the skill participates in (so the G3 check finds coverage).Samples and eval sets are the evidence layer. The deterministic G3 baseline (presence + the regression signal) is enforced by library-regression; behavioral judging of the cases is the opt-in askit-evaluate behavioral mode (delegated to askit-quality-grader), never the CI gate (Design Principle 3). Example-threads (the bounded validation triad of ADR 0021: a greenfield Bronze plugin, the pm-skills adopt-and-grade thread, and the toolkit itself as Gold) anchor samples to real end-to-end arcs rather than isolated snippets.