commit-history

List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.

Quality

87%

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

96%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.

A tight, highly actionable body: concrete call syntax, an expected-output example, explicit defaults, a genuine anti-pattern (URL-encoding the REST fallback), and error-recovery for empty results, all with zero padding. The only structural weakness is the single unverified reference to a shared troubleshooting file outside the bundle.

Suggestions

Verify or inline the ../_shared/TROUBLESHOOTING.md reference, or state the expected failure behavior directly, so the skill does not depend on a file whose presence cannot be confirmed from the bundle.

Consider a one-line note on how to handle a failed or partial memory_commits response, not just the empty and tool-unavailable cases.

Dimension	Reasoning	Score
Conciseness	Every section earns its place: a minimal quick-start with example call and expected output, a two-sentence 'Why' carrying non-obvious guidance ("An empty result means the filter matched nothing, not that work is missing"), and no padding or explanations of concepts Claude already knows. Clear match for anchor 5 ('lean and efficient; every token earns its place').	5 / 5
Actionability	The skill provides a copy-paste-ready tool call (memory_commits { "branch": "main", "limit": 20 }), an expected-output block that doubles as the rendering template, explicit defaults and caps (limit 100, max 500), and concrete URL-encoding functions (URLSearchParams/encodeURIComponent) plus the exact endpoint path. Fully executable guidance covering the common case, matching anchor 5.	5 / 5
Workflow Clarity	A clear four-step sequence: parse with defaults, call the tool, render reverse-chronologically, and an explicit error-recovery step for the empty result ("suggest dropping the branch or repo filter"), reinforced by a checklist. It is a read-only, single-task skill with nothing destructive to validate, so no validation gap exists; this matches anchor 5's feedback loops and checklist.	5 / 5
Progressive Disclosure	Sections are well-organized and the references ('See also' sibling skills, ../_shared/TROUBLESHOOTING.md) are one level deep and clearly signaled, with no content that belongs in a separate file inlined. Held at anchor 4 rather than 5 because ../_shared/TROUBLESHOOTING.md lies outside the bundle and cannot be verified to exist, leaving one navigation path unconfirmed.	4 / 5
	Total	19 / 20 Passed

Description

78%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 well-formed description with an explicit 'Use when...' clause and natural quoted trigger phrases. Third-person imperative voice is used correctly. The main weakness is that the capability list is a single action with filters rather than an enumeration of what is rendered, which leaves it slightly under-specified and mildly overlapping with generic git-log requests.

Suggestions

Enumerate what is rendered (short sha, branch, timestamp, first line of message, linked session ids) to lift specificity from naming one action to listing several concrete capabilities.

Add common trigger synonyms such as 'git log', 'recent commits', or 'commit history' to the when-clause so users phrasing the request generically still match.

Sharpen distinctiveness by leading with the agent-session linkage (e.g. 'List git commits linked to agent sessions...') so it is less likely to trigger for plain git-log requests.

Dimension	Reasoning	Score
Specificity	"List recent git commits linked to agent sessions, optionally filtered by branch or repo" names the domain and one concrete action with filters, but does not enumerate what is rendered (sha, message, session ids, counts). This matches anchor 3 (1-2 concrete actions, not comprehensive); it is not 4 because filtering is a modifier on the single list action rather than several distinct capabilities.	3 / 5
Completeness	It explicitly answers both what ("List recent git commits linked to agent sessions, optionally filtered by branch or repo") and when ("Use when the user asks 'show agent commits'...") with concrete trigger phrases. This is a clear match for anchor 5; anchor 4 would require a weaker or less explicit 'when' clause.	5 / 5
Trigger Term Quality	Natural quoted phrases like "show agent commits", "what has the agent shipped", and "list linked commits" would plausibly be said verbatim by users. Not 5 because common variations such as "git log", "recent commits", or "commit history" are missing.	4 / 5
Distinctiveness Conflict Risk	The agent-session linkage and triggers like "what has the agent shipped" carve a distinct niche, but the opening "List recent git commits" could plausibly fire on a generic git-log request. Minor overlap risk with closely related git skills places this at anchor 4 rather than 5.	4 / 5
	Total	16 / 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-history/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.