Claude Skills by alunduil

Decide where a new tool slots into the chezmoi bootstrap and README. Use when adding a CLI/binary to the host bootstrap so it lands in the right install pass and the right README block. Routes auth-required tools to "Interactive logins" and fire-and-forget binaries to "PATH check".

Audit, write, or revise Architecture Decision Records (ADRs), including the decision of whether one is warranted. Use when an architecturally significant decision needs recording, when reviewing an existing ADR collection, or when adding ADRs to a project that has none. Detects existing template (Nygard or MADR) and defaults to Nygard for new repos. Gates comparison ADRs through a decompose-and-verify interview before drafting.

Audit, write, or update CHANGELOG.md following Keep a Changelog 1.1.0. Use when creating a CHANGELOG, or reviewing commits to ensure Unreleased reflects user-visible changes. Defers to auto-managed setups (changesets, release-please, git-cliff, semantic-release, towncrier) and applies semver 2.0.0 — or Haskell PVP for Haskell projects.

Query Codecov for flaky-test signal, failure history, and coverage data via the codecov-api wrapper. Use when asked about flaky tests, intermittent test failures, why a test is failing, coverage on a PR/file/branch, or whenever browser access to Codecov is blocked by the login wall.

Audit, write, or revise CONTRIBUTING.md, including the decision of whether one is warranted. Use when creating contribution guidance, editing existing CONTRIBUTING, or when a README points to missing/thin contribution docs. Applies the nayafia/contributing-template framework.

Audit, write, or revise a data flow diagram (DFD). Use when asked to draw or model how data moves through a system, when standing up a DFD with trust boundaries for threat modeling or security review, or when checking an existing DFD for drawing and balancing errors. Pins Mermaid `flowchart` as the output notation and the correctness rules a DFD must satisfy.

Audit, write, or revise docs under `docs/` (or repo equivalent) when the artifact is a tutorial, how-to, reference, or explanation — anything not already a README, CONTRIBUTING, ADR, or CHANGELOG. Forces a Diátaxis mode pick before writing, then loads mode-specific anti-patterns. Use when creating or editing a tutorial/how-to/reference/explanation doc, or when prose drifts across modes (the canonical case: a how-to growing explanatory paragraphs).

File a new GitHub issue in the checked-out repo — search first for duplicates/adjacent issues to update or reference, detect the repo's issue template if any, then compose title/body/labels/milestone matching house style. Use when asked to file, create, open, report, or track an issue.

Relate GitHub issues and PRs — pick the right edge type (blocked-by via GraphQL, parent/sub-issue, Closes/Fixes in PR body, plain mention) and apply it. Use when asked to link, block, depend on, make a subtask of, or close-on-merge.

Pick up an existing GitHub issue in the checked-out repo — implement from scratch or take over an in-flight PR. Use when asked to work, take, implement, fix, or close issue #N. Confirms relevance before coding (comments, recent commits, linked PRs/branches), surfaces a go/no-go on staleness, then commits incrementally.

Create, name, scope, assign, and close GitHub milestones. Use when adding a milestone, deciding whether work belongs in one, or naming the next one. One axis per project (release / date / theme); never as labels.

Open a GitHub PR with a tight body — why this change, what'll surprise the reviewer, how we know it's correct — or add a pull_request_template to a repo. Use when asked to open, create, or draft a pull request, compose or regenerate a PR description, or scaffold a repo's PR template. Composes the Summary/Gotchas/Verification structure and detects an existing template first.

Review a pull request's diff against the cross-repo judgment bar — correctness, secrets, inline suppressions, matching the repo's conventions, docs, commits, and the test plan. Use when asked to review a PR or a branch diff for what the repo's linters, type checkers, and scanners can't assert. Assumes the sensors are green and reviews only the residue.

Audit, write, or revise README.md. Use when creating a README, editing one, or noticing smells (missing badges, no install steps, unclear purpose, no engagement guidance). Applies ddbeck's checklist and a shields.io badge principle.

Audit, write, or revise renovate.json. Use when adding Renovate, troubleshooting unexpected (or missing) update PRs, hardening against supply-chain attacks, or evolving an existing config.

Audit, write, or revise a threat model using STRIDE. Use when asked what could go wrong with a system, to threat-model or security-review a design, to enumerate threats against a component or data flow, or to check an existing threat model for coverage gaps or stale mitigation claims. Walks a data flow diagram element by element, pins the threat table as the output artifact, and makes every row cite the code that makes its claim true.

Audit, write, or revise .vale.ini, or work through vale findings on a repo. Use when adding Vale, troubleshooting silent passes or noisy findings, evolving config, or applying the suggestion → warning → error cleanup cascade after a vale run (interactive or pre-commit failure). Applies the two-hook pre-commit pattern (sync + lint), explicit Packages and per-format BasedOnStyles, scoping/ignores for false positives, and a shared accept.txt vocabulary.