跳到正文
cccskills
免费在 GitHub 公开

project-learnings

Captures project-specific patterns and anti-patterns into the project documentation. Loaded by other skills when they discover project-specific knowledge worth encoding for future sessions.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md5.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Project Learnings

Capture project-specific patterns and anti-patterns into the project's instruction file (e.g., CLAUDE.md). This creates a self-improving feedback loop where discoveries from debugging, development, and review make future sessions smarter.

Only project-specific knowledge qualifies. Generic programming advice does not belong in the project instruction file.


Step 1: Evaluate Discovery

Determine if the finding qualifies as project-specific. The finding must pass at least ONE of these criteria:

CriteriaExample That QualifiesExample That Doesn't
Would a developer unfamiliar with this project likely hit this issue?"The processOrder() function expects amounts in cents, not dollars""Always validate function inputs"
Is this pattern specific to this codebase's architecture, APIs, or conventions?"The UserProfile type has an optional metadata field that is always present at runtime""Use TypeScript strict mode"
Is it something generic training data wouldn't cover?"Never call db.query() without the timeout option — the default is infinite""Use async/await instead of callbacks"

If NO to all criteria, STOP. Do not add generic programming knowledge to the project instruction file. Return to the calling skill and report that no project-specific learning was found.

If YES to any, proceed to Step 2.


Step 2: Read Existing Project Instruction File

  1. Find the project's instruction file:

    • Check the repository root first for CLAUDE.md or equivalent
    • If not found, check if there's a project-level .agents/ directory
  2. Parse existing content:

    • Understand the existing structure, headings, and conventions
    • Look for sections where this learning would fit (e.g., "Known Gotchas", "Bug Patterns", "Conventions", "Known Challenges")
    • Check for duplicate or similar entries already present
  3. If a similar entry already exists, STOP. Report to the calling skill that this knowledge is already captured. Do not create duplicates.

  4. Identify placement:

    • If an appropriate section exists, plan to add the entry there
    • If no appropriate section exists, plan to propose a new section (e.g., ## Known Gotchas or ## Project-Specific Patterns)
    • New sections should be placed after the main documentation sections but before appendices or settings

Step 3: Format the Learning

Write a concise, actionable instruction following these rules:

Format:

  • Use imperative form: "Always validate X before calling Y"
  • Include the WHY: "...because the API returns dates as strings, not Date objects"
  • Keep it to 1-3 lines
  • Follow the existing file style and conventions

Templates:

For bug patterns:

- **[Area/Component]**: [What to do/avoid] — [why, with specific details]

For API gotchas:

- `functionName()` in `path/to/file`: [What's surprising about it] — [consequence if ignored]

For architectural constraints:

- [Constraint description] — [why it exists and what breaks if violated]

Examples of well-formatted learnings:

  • Order processing: Always multiply amounts by 100 before passing to processOrder() — it expects cents, not dollars
  • db.query() in src/database.ts: Always pass the timeout option — the default is infinite and has caused production hangs (30 second timeout recommended)
  • Never import from internal/ directories in src/api/ — the build system treats these as separate compilation units and circular dependencies will silently break HMR

Step 4: Confirm with User

Prompt the user:

Show:

  1. The exact text to be added
  2. Where it will be placed in the project instruction file (section name, after which line/entry)
  3. Why this qualifies as project-specific

Options:

  • "Add this" — Write the entry as proposed
  • "Edit before adding" — User provides modified text, then write that instead
  • "Skip" — Do not add anything, return to calling skill

Step 5: Write Update

If the user confirmed (or provided edited text):

  1. Add the entry to the project instruction file at the identified location
  2. If a new section was needed, create the section heading first
  3. Verify the edit was applied correctly by reading the modified area
  4. Report success to the calling skill with a summary of what was added

If the user chose "Skip":

  • Report to the calling skill that the learning was declined
  • Do not modify any files

Integration Notes

This skill was converted from the dev-tools plugin package. It is typically loaded by other skills (such as bug-killer and feature-dev) when they discover project-specific knowledge worth encoding for future sessions. No external dependencies are required.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Analyze test coverage and identify gaps with actionable recommendations

中文简介正在准备中。当前显示原文说明。

sequenzia/agent-alchemy452026年6月1日 更新

Analyze an existing spec for inconsistencies, missing information, ambiguities, and structure issues. Use when user says "analyze spec", "review spec", "spec quality check", "validate requirements", "audit spec", or "check spec quality".

中文简介正在准备中。当前显示原文说明。

sequenzia/agent-alchemy452026年6月1日 更新

Provides architectural pattern knowledge for designing feature implementations including MVC, event-driven, microservices, and CQRS patterns. Use when designing system architecture or choosing implementation patterns.

中文简介正在准备中。当前显示原文说明。

sequenzia/agent-alchemy452026年6月1日 更新

Executes diagnostic investigation tasks to test debugging hypotheses. Runs tests, traces execution, checks git history, and reports evidence. (converted from agent)

中文简介正在准备中。当前显示原文说明。

sequenzia/agent-alchemy452026年6月1日 更新

Systematic, hypothesis-driven debugging workflow with triage-based track routing. Use when asked to "fix this bug", "debug this", "why is this failing", "this is broken", "investigate this error", "track down this issue", or any debugging situation. Supports --deep flag to force full investigation.

中文简介正在准备中。当前显示原文说明。

sequenzia/agent-alchemy452026年6月1日 更新

Systematic, hypothesis-driven debugging workflow with triage-based track routing. Use for debugging, fixing bugs, and investigating errors.

中文简介正在准备中。当前显示原文说明。

sequenzia/agent-alchemy452026年6月1日 更新

查看 sequenzia 的全部技能

报告此技能的问题