Run a full Section 508 + WCAG 2.2 Level AA accessibility audit on a federal / .gov / public-sector website or ICT product. Triggers: "Section 508", "508 audit", "WCAG", "VPAT", "ACR".
中文简介正在准备中。当前显示原文说明。
Run a full retrospective and dev cycle analysis. Chains /recall → /new-features to reconstruct what went wrong, extract lessons learned, identify rework patterns, and synthesize feature ideas from the findings. Triggers: retrospective, retro, dev cycle analysis, what went wrong, lessons learned, postmortem, sprint retro.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
You are an autonomous retrospective-to-ideation agent. Do NOT ask the user questions. Run the full pipeline below without pausing between phases.
TARGET: $ARGUMENTS
If arguments are provided, use them to scope the retrospective (branch name, date range, feature). If no arguments are provided, analyze the full git history.
PARALLEL EXECUTION: After /recall completes and produces findings, use the Agent tool to run follow-up analyses concurrently.
Follow the instructions defined in the /recall skill exactly.
Produce the full retrospective output: Timeline Reconstruction, Pattern Extraction, Dependency Mapping, and Insight Distillation.
Save the retrospective output to docs/dev-retrospective.md (create the docs/ directory if it doesn't exist).
Key outputs to preserve for Phase 2:
Do NOT stop here. Continue immediately to Phase 2.
Now follow the instructions defined in the /new-features skill exactly.
Read ALL .md files in the docs/ directory — this includes
the docs/dev-retrospective.md you just wrote plus any other markdown files
that already existed in the folder.
Extract learnings from every file, synthesize feature ideas, and write
the report to docs/NewFeatures-X.md (where X is a 3-word kebab-case theme).
IMPORTANT: Features should directly address the pain points and inefficiencies discovered in the retrospective:
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
When both phases are complete, print a summary:
Files generated:
docs/dev-retrospective.md — Full development cycle analysisdocs/NewFeatures-[X].md — Feature ideas derived from retrospective learningsKey stats:
Top insight: [single most impactful finding from the retrospective]
Next steps:
/spec [feature name] to generate implementation stories/iterate to start building a feature/research to validate features against competitorsAfter producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /retro — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}
Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
STRICT RULES:
docs/dev-retrospective.md so Phase 2 can read it.docs/ directory./recall and /new-features apply to their respective phases.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Run a full Section 508 + WCAG 2.2 Level AA accessibility audit on a federal / .gov / public-sector website or ICT product. Triggers: "Section 508", "508 audit", "WCAG", "VPAT", "ACR".
中文简介正在准备中。当前显示原文说明。
Analyzes actuarial modeling systems for loss reserving accuracy, premium pricing methodology, mortality/morbidity tables, stochastic modeling, and capital adequacy per SOA and Solvency II standards..
中文简介正在准备中。当前显示原文说明。
Analyzes advertising yield across programmatic and direct-sold inventory including CPM/CPC/CPA performance, header bidding efficiency, fill rate optimization, inventory monetization strategies, and compliance with IAB standards and OpenRTB protocols..
中文简介正在准备中。当前显示原文说明。
Create and manage Architecture Decision Records using the Michael Nygard format. Triggers: you need to document architecture decisions, record technical choices, explain why a technology was chosen.
中文简介正在准备中。当前显示原文说明。
Analyzes affordable housing management software for unit allocation algorithms, waitlist management, income verification workflows, Fair Housing compliance, LIHTC and Section 8 program tracking, inspection scheduling, and tenant reporting..
中文简介正在准备中。当前显示原文说明。
Rewrites existing landing pages, blog posts, and documentation so AI search engines (Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini) cite them. Triggers: an existing page underperforms in AI answers despite ranking well in classic SERPs.
中文简介正在准备中。当前显示原文说明。