agentsclimarketplace

Git history investigation

Skill planifest/planifest-framework/planifest-framework/external-skills/git-history-investigation

A specification framework for agentic development. Agents build from complete specs - not guesses.

Install
npx -y skills add planifest/planifest-framework --skill git-history-investigation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Reconstruct change history using log/show/diff/blame evidence to explain when and why behavior changed. Use when teams need evidence-based history analysis for regressions or ownership questions; do not use for CI workflow design or application behavior implementation.

SKILL.md

2.1 KB, 376 tokens by cl100k_base, as published. Nobody here has run it

Git History Investigation

Overview

Use this skill to produce an auditable evidence chain from symptom to likely root-cause commits.

Scope Boundaries

  • Use this skill when the task matches the trigger condition described in description.
  • Do not use this skill when the primary task falls outside this skill's domain.

Shared References

  • Evidence quality rules:
    • references/history-evidence-quality-rules.md

Templates And Assets

  • Investigation log:
    • assets/history-investigation-log-template.md
  • Root-cause hypothesis template:
    • assets/root-cause-hypothesis-template.md

Inputs To Gather

  • Reproducible symptom or unexpected behavior.
  • Candidate paths/modules and relevant time window.
  • Issue/PR/review metadata for context.
  • Required confidence threshold for decision-making.

Deliverables

  • Chronological evidence trail.
  • Root-cause hypothesis with alternative hypotheses.
  • Confidence-rated conclusion and next action recommendation.

Workflow

  1. Define scope and symptom timeline in assets/history-investigation-log-template.md.
  2. Gather direct evidence from log/show/diff/blame.
  3. Form and test hypotheses with assets/root-cause-hypothesis-template.md.
  4. Apply references/history-evidence-quality-rules.md to validate claim strength.
  5. Publish findings and root-cause-oriented follow-up actions.

Quality Standard

  • Evidence chain links symptom timeline to concrete commit behavior.
  • Root-cause claim includes supporting and disconfirming evidence.
  • Alternatives are explicitly considered and resolved.
  • Follow-up actions address cause, not just surface symptoms.

Failure Conditions

  • Stop when symptom cannot be scoped to a meaningful history window.
  • Stop when evidence is mostly inferential without diff-level support.
  • Escalate when confidence is too low for production-impacting decisions.

What ships with it: 1 file

11.3 KB alongside SKILL.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.