Index of every page on this site: llms.txt
All skills
qoderai avatar

/change-traceability-review

@c6240a8
by qoderaiqoderai/better-harness2.5k stars
208
Run it yourself

Use for change traceability review across specs, commits, PRs, branches, local diffs, and git history, including Spec Preparation, Review Readiness Checks, and Review Retrospectives, to generate or verify Story-linked specs, commit-message evidence, test evidence, risk signals, AI involvement, and review-flow improvement suggestions.

Use this Skill: https://skilld.dev/gh/qoderai/better-harness/change-traceability-review

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesmode-rules.md

≈546 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Mode Rules

Traceability Rules

Find Story/issue evidence in order: Story: footer or explicit PR field; subject/body tokens like [A-Z][A-Z0-9]{1,9}-[0-9]+, STORY-123, or repo-established #123; branch or PR text; doc/spec path or historical commits mentioning the same token. Count only literal visible tokens. Do not infer a Story from topic similarity, timestamps, branch slugs, or repeated module names.

If Story/issue evidence exists, search for Spec evidence: explicit Spec:; matching local docs; historical spec-doc commits like docs(spec): ...; key terms from the commit summary.

If Spec evidence exists, verify it is linked back to the same literal Story when one exists, then compare changed files and tests against the spec's Acceptance Scenarios, Plan and Tasks, and Test and Review Evidence. Classify code-without-spec, spec-without-code, and spec-drift separately.

Classify evidence as confirmed, candidate, missing, or unavailable. External trackers and CR links are unavailable unless actually opened or provided.

Analysis Rules

For Review Readiness Check, inspect Story evidence, Spec, Test, Risk, AI, Refs; changed files/modules, generated code, sensitive paths, deleted guards, staged vs unstaged split, unrelated changes; tests from changed test files, Test:, validation output, or CI text.

For Spec Preparation, first find a literal Story/issue or ask for one if it is required and unavailable. Draft or update the spec with AC ids, non-goals, plan/tasks, and test/review evidence. End with a normal commit-body sentence that mentions the Story when present, spec path, and validation evidence.

For Review Retrospective, aggregate before expanding: separate automation/merge commits first so scm-auto, CodeFlow, or merge commits do not skew developer metrics; count type/scope, Story evidence, Spec, Test, Risk, AI, Refs; identify Story IDs without local Spec, spec-doc-before-implementation patterns, large commits, mixed scopes, weak subjects, rework words, repeated same-module fixes, and AI/automation markers.

Do not rank people or infer intent. Frame history findings as review-system improvements.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning3mo3 checks · Risk MEDIUM
  • Gen Agent Trust Hub3mo

    The skill helps perform traceability reviews by executing local git and search commands. It is vulnerable to command injection if user-provided identifiers, such as Story IDs, are not properly sanitized before being passed to shell commands. Additionally, the skill processes external content including git logs, diffs, and specification documents which could contain malicious instructions designed to manipulate the agent's behavior through indirect prompt injection.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Signed by skilld at c6240a8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 4 months ago

README badge

README badge for qoderai/better-harness/change-traceability-review