commit-context

Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary lean skill body: executable commands with concrete examples, a clearly sequenced three-step workflow with explicit error-case handling and a verification checklist, and clean section structure with no padding. The instruction-only format is fully appropriate given the concrete, specific guidance provided.

Dimension	Reasoning	Score
Conciseness	The ~58-line body is lean and assumes Claude's competence throughout: no git or session-tracking concepts are explained, every section (Quick start, Why, Workflow, Anti-patterns, Checklist, See also, Troubleshooting) earns its place, and the example is minimal but complete. Nothing matches the over-explanation patterns of the lower anchors.	5 / 5
Actionability	All guidance is copy-paste executable with real arguments and a concrete expected-output sample: `git blame -L 40,52 src/auth/refresh.ts`, `git log -L :<function>:<file>`, `git log -n 1 -- <file>`, and `memory_commit_lookup { "sha": "..." }`. The WRONG/RIGHT anti-pattern pair shows exactly what output to produce in the null case, covering the main cases per the top anchor.	5 / 5
Workflow Clarity	The three-step workflow (find SHA → lookup → present) is clearly sequenced, and it includes explicit checkpoints: the `commit: null` case is handled with a directed recovery message, and the Checklist section verifies each step (SHA provenance, no fabricated sessions, verbatim quoting). This is a read-only lookup skill, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	This is a short, single-purpose skill with no bundle files (no references/, scripts/, or assets/ directories), so nothing needs splitting; sections are well-organized and navigable. The one external pointer (../_shared/TROUBLESHOOTING.md) is clearly signaled, condition-scoped, and one level deep, satisfying the simple-skill guideline for a top score.	5 / 5
	Total	20 / 20 Passed

Description

86%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit what/when structure and excellent natural-language trigger phrases. Its only weakness is that it advertises a single trace action while the skill body performs several more (commit presentation, session listing, memory recall), leaving capability coverage incomplete and creating minor overlap risk with sibling history skills.

Suggestions

Enumerate one or two more concrete capabilities in the description (e.g. presenting the commit and its linked agent session's observations), so specificity moves from one action to several.

Narrow the broadest trigger ("who wrote this") toward the agent-session context (e.g. "who or which agent session wrote this") to reduce overlap with plain git-authorship questions and sibling skills like commit-history.

Dimension	Reasoning	Score
Specificity	The description names one concrete, well-defined action ("Trace a file, function, or line back to the agent session that produced its current commit") with enumerated target types, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It stays at 3 because it lists only a single action rather than several — it omits downstream actions the skill actually performs (presenting commit details, listing linked sessions, recalling observations).	3 / 5
Completeness	It explicitly answers both what ("Trace a file, function, or line back to the agent session that produced its current commit") and when (an explicit "Use when the user asks..." clause with concrete quoted trigger phrases), exactly matching the anchor-5 example pattern.	5 / 5
Trigger Term Quality	It directly quotes the natural phrases a user would say — "why is this code here", "what was the agent doing when this changed", "who wrote this" — plus a paraphrased case ("wants context on a specific location in the codebase"), giving comprehensive synonym-level coverage per the top anchor.	5 / 5
Distinctiveness Conflict Risk	The agent-session attribution niche is clear and distinct from general git skills, but the triggers "who wrote this" and "context on a specific location" are broad enough to fire on ordinary git-authorship questions where a sibling skill (e.g. commit-history) would be the better target — minor overlap risk rather than minimal, matching anchor 4. It is well above anchor 3 because the core framing (tracing code to the producing agent session) is unmistakably niche-specific.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rohitg00/agentmemory
Path: plugin/skills/commit-context/SKILL.md
Commit: c314c7b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.