Каталог навыков агентов

Refine an existing GitHub issue for clarity and completeness; use when asked to improve an issue draft.

After a verify-goal run, turn the ledger into the next iteration: tighten criteria that passed by accident, add the crit...

Refine a GitHub issue with extra validation and triage detail; use for high-impact issues or cross-team work.

Break down issues into sub-tasks with dependencies. Supports Linear and Jira backends. Use when the user mentions "refin...

Runs a safe, resumable refinement loop over a working repository. It discovers behavior-preserving improvements through...

Use when the user asks to refine, polish, or keep improving a repo and no specific tasks remain.

Reframes implementation descriptions into outcome statements. Invoked by launch commands during outcome refinement.

Refines an existing implementation plan through discussion with the user. Takes a GitHub issue number. Use when the user...

Iteratively review and revise a planning artifact until no new findings survive evaluation. Supports plans, shells, and...

Iteratively review and revise plan shells until no new findings survive evaluation. Runs /review-plan-shells, /evaluate-...

Triage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for...

Use this skill when the user's request is vague, incomplete, or poorly structured and needs to be sharpened into a detai...

Reconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work "…"',...

This skill should be used when the user asks to "refine a prompt", "optimize a prompt", "improve my prompt", "rewrite pr...

Iteratively review and revise a prompt plan until no new findings survive evaluation. Runs /review-prompt-plan, /evaluat...

Refine vague or unclear prompts into precise, actionable instructions. Use when user asks to clarify or improve instruct...

Stage 2 skill of /arch. Reads the /specify quality profile, refines targets against architectural reality (inventory con...

Refine requirements from discoveries during TDD/BDD implementation. Captures edge cases, race conditions, and business r...

Refine and clarify feature requirements by asking targeted follow-up questions, then update or create tasks based on ans...

Refine a provisional VDM-SL specification through dialogue with the user, uncovering the true specification that exists...

Iteratively review and revise a specification document until no new findings survive evaluation. Runs /review-spec, /eva...

Transform vague or incomplete user stories into sprint-ready stories with clear acceptance criteria, test scenarios, and...

Review one Jira or GitHub work item for implementation readiness and produce one tracker-facing refinement comment or dr...

Refine a development ticket — or brainstorm a raw idea — into a validated, self-contained REQUIREMENTS document — the "w...

Refine a Jira/Linear ticket before planning — 'refine ticket', 'tighten AC on PROJ-123', 'ist das Ticket klar?'; rewritt...

Use when analyzing workflow effectiveness or identifying skill extraction opportunities - systematically identifies patt...

Carefully curated, modern minimal style with elegant serif typography and understated, sophisticated palettes.

Move a skill from staging to active

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Decide whether a design needs a redesign or a refinement, and when it's a refinement, keep the structure and fix only th...

要件定義の抜け漏れを質問形式で洗い出し、仕様を精緻化

Generate systematic refinement steps from high-level specifications to concrete implementations in Isabelle/HOL or Coq,...

Quality assurance orchestrator that refines outputs from other skills using standards-based evaluation and iterative imp...

Update existing Lattice standards after a significant change — the update-mode counterpart to lattice-init. Scans .latti...

Convergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses,...

Transform raw ideas into structured Product Requirements Documents (PRDs) using systematic refinement

DMA merge queue pattern for sequential, deterministic merge request processing. Checks out branches, rebases onto main,...

Refining and improving user prompts for StickerNest development. Use when the user asks to improve a prompt, make a requ...

Improves specification quality through completeness checks, clarity verification, and structured feedback. Use when spec...

Use when anything misbehaves - a failing test, a production bug, a build break, flaky or unexpected behavior - before pr...

Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, friction reports, logs, a...

Self-improvement through conversation analysis. Extracts learnings from corrections and success patterns, proposes updat...

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit o...

End-of-day reflection — what worked, what surprised, message to tomorrow. Saves to running journal. Use when asked to "r...

Extract durable, non-obvious lessons from the current dialogue and route them to project guidance, memory, documentation...

Run a reflection ritual. Invokes Ada.

Use when the user says 'we decided', 'I realized', or 'that's a pattern' — captures a share-ready decision, finding, or...

Reflect on the conversation and persist learnings to project documentation

Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvemen...

Reflect on the current session — what went well, what didn't, and any suggestions for improving the workflow or project...

Review active-task history through judgment, tooling, and divergent lenses, then propose durable skill improvements. Use...

Mid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, a...

Use for "reflect", after a complex task lands cleanly, after the human corrected your approach mid-task, or when a workf...

Use when approved session lessons should become durable workflow improvements.

Use when the user asks to reflect on the CURRENT session or one transcript file they name, analyze the agent's own proce...

ONLY on /reflect or retro step 4. Propose skill improvements.

Reflect on a session to identify learnings, friction points, and improvements. Captures valuable insights for future ses...

Analyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user c...

Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after...

Use this skill when capturing user corrections, feedback, or learnings from a session to permanently improve other skill...

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or p...

Deep reflection on the skill learning system itself. Analyzes what's working, what's stale, and proposes structural impr...

Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity tri...

Capture session knowledge (gotchas, patterns, integration quirks) into the project's knowledge base. Use when: session i...

Use when a completed task needs reflection on the invoked skills to propose and apply approved improvements, with explic...

Use when a completed task needs reflection on invoked skills to propose and apply approved improvements. Not for remote,...

Analyze the current session and consolidate learnings. Use at the end of a session or task.

CRITICAL learning capture. Extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes an...

Think through any decision — code, business, personal — and get a straight answer. Fires on "reflect on X", "start from...

Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR c...

Analyze the current conversation for corrections, approvals, and patterns, then propose updates to the skill files that...

Self-reflection on recent activity to identify patterns and improvements

Delegate three parallel reviewers over the active thread, surface learnings, and route each to a concrete edit on an exi...

Analyze workflow runs and produce a daily reflection.

User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge ca...

Extracts learnings from completed work, feedback, or failures. Updates a persistent learnings file with capped entries....

Analyze user corrections, read session transcripts, and proactively update .claude/rules/ or SKILL.md files to prevent r...

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete c...

Use when the user asks to review PAST sessions, find recurring patterns across sessions, or improve project primitives (...

Diagnostic tool for validating SpecWeave reflection system health and troubleshooting issues. Use when reflection seems...

Clear specific learnings from CLAUDE.md Skill Memories section. Activates for reflect clear, clear learning, remove lear...

Internal reflection stage that groups durable run signals by skill and emits validated handoffs to skill-lab improve whe...

Use when the user asks to close a session by auditing it AND writing the fixes into the project's instruction files — au...

Disable automatic reflection on session end. Manual reflection still works. Activates for reflect off, disable reflect,...

Enable automatic reflection on session end. Stop hook will analyze session and extract learnings automatically. Activate...

Pattern for producing quality reflections after completing work. Required for all agent outputs.

Detects when a stated outcome names a specific instance — a mechanism-as-means or a single named product — where a categ...

Guide an end-of-session reflection to capture learnings and feelings. Use when finishing a work session, after completin...

反思总结的 Skill。当任务完成或失败后需要复盘时触发。触发词：反思、复盘、总结、reflect、回顾、lessons learned。

Show reflection configuration and learning statistics. Activates for reflect status, reflection status, memory status, l...

Use when completing a plan, finishing a development branch, wrapping up a session, or at any natural transition between...

Analyze development sessions, capture learnings, and improve Claude Code instructions. Use when the user wants to reflec...

Automatic quality check on significant outputs via isolated sub-agent. Spawns reflection-agent for objective evaluation...

Use when the user invokes $reflection or asks for an independent, concise post-task audit of whether Codex overthought a...

Self-improving meta-skill that learns from user corrections and updates the TARGET PROJECT's skill files. Only runs when...