agentleFS
dativo-iodativo-io/talon/.claude/skills/implement-issue/SKILL.md

implement-issue

Skill18 starsChanged 22 days agoApache-2.0View on GitHub

Implement a Dativo Talon GitHub issue from investigation through verified handoff.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-issue, create-issue and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ravihammondSkill

    review-issue

    Review and repair one GitHub issue implementation in the current checkout.

    Also in 4 projects that use this

  • sahinSkill

    create-issue

    Also in 6 projects that use this

  • TermiX-officialSkill

    merge-pr

    Merge a GitHub PR via squash after /preparepr. Use when asked to merge a ready PR. Do not push to main or modify code. Ensure the PR ends in MERGED state and clean up worktrees after success.

    Also in 3 projects that use this

  • ShopifySkill

    triage-issue

    Triage a GitHub issue — classify priority (P0/P1/P2), search for duplicates, and apply labels.

    Also in 3 projects that use this

  • SentrySkill

    create-pr

    Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.

    Also in 5 projects that use this

  • OpenAISkill

    writing-skills

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the complete current issue and linked blocking/dependent issues.

    line 11
  2. Distinctive:

    If the issue affects product/architecture direction, read current #265.

    line 12
  3. Very specific:

    Do not treat historical comments, old docs, or agent memory as newer than the current issue/code/tests.

    line 23
  4. Distinctive:

    Do not create speculative abstractions or duplicate sources of truth.

    line 29
  5. Distinctive:

    Add the lowest useful regression first, then implementation.

    line 30
  6. Very specific:

    Add integration/E2E coverage when the contract crosses a real storage/API/runtime/protocol boundary.

    line 31
  7. Very specific:

    Update docs/CHANGELOG/LIMITATIONS only to describe behavior actually implemented.

    line 32
  8. Very specific:

    Run the /verify-change ladder, in order as appropriate:

    line 36
  9. Very specific:

    When a contract surface changed (machine code, evidence annotation, config field, pricing entry, smoke section), complete the registration …

    line 43
  10. Very specific:

    Do not commit, push, mutate the issue, or create a PR unless the user's task explicitly authorizes it.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Implement GitHub issue $ARGUMENTS.

Before editing

  1. Read the complete current issue and linked blocking/dependent issues.
  2. If the issue affects product/architecture direction, read current #265.
  3. Inspect the relevant implementation and nearest tests.
  4. State:
    • current behavior;
    • target behavior;
    • invariants and trust boundaries;
    • compatibility/persistence implications;
    • explicit non-goals.
  5. Identify the smallest coherent implementation.
  6. For non-trivial changes, present the plan before editing.

Do not treat historical comments, old docs, or agent memory as newer than the current issue/code/tests.

Implement

  • Stay inside issue scope.
  • Reuse canonical state, policy, evidence, projection, and error paths.
  • Do not create speculative abstractions or duplicate sources of truth.
  • Add the lowest useful regression first, then implementation.
  • Add integration/E2E coverage when the contract crosses a real storage/API/runtime/protocol boundary.
  • Update docs/CHANGELOG/LIMITATIONS only to describe behavior actually implemented.

Verify

Run the /verify-change ladder, in order as appropriate:

  1. focused/changed-package tests (race detector on for anything concurrent);
  2. relevant integration tests;
  3. relevant E2E/smoke proof;
  4. broader repository checks when required (make check, go test ./tests when docs changed).

When a contract surface changed (machine code, evidence annotation, config field, pricing entry, smoke section), complete the registration set in .claude/rules/contract-surfaces.md.

Inspect the final diff and compare it against every acceptance criterion.

Do not commit, push, mutate the issue, or create a PR unless the user's task explicitly authorizes it. When it does, follow /prepare-pr.

Handoff

Report:

  • files/areas changed;
  • important design decisions;
  • acceptance criteria satisfied;
  • exact tests run and results;
  • unresolved limitations, risks, or follow-up work.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.