CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gitcrawl/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

The body is an exemplary lean skill: executable commands with concrete output fields, an implicit but coherent discover-verify-act workflow with freshness validation before mutations, and clean sectioning with one well-signaled external link. The only improvements are showing the remaining described commands (the sqlite3 query, the maintainer commands) and making the discover→sync→verify sequence explicit.

DimensionReasoningScore

Conciseness

The body is lean, dense, and imperative throughout ("Check freshness and configured database paths with `gitcrawl doctor --json`"); it assumes Claude's competence and every token earns its place with no padding or explanations of known concepts.

5 / 5

Actionability

Copy-paste-ready command blocks with concrete JSON field lists (threads, neighbors, search, clusters, gh pr view/checks/issue view) cover the common cases, but a few invocations are described rather than given, e.g. no full `sqlite3 -readonly` example and "maintainer commands" are referenced without being shown.

4 / 5

Workflow Clarity

A clear ordered flow is present (archive discovery → `doctor --json` freshness check → bounded sync if stale → `gh` live verification before any maintainer decision or public mutation) with an explicit validation checkpoint, so the destructive-operation cap does not apply; it falls short of 5 only because the sequence is implicit in prose rather than an explicit step checklist with error-recovery loops.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files; sections (overview/commands, Current GitHub State, Archive Boundaries) are well-organized with a single clearly signaled one-level-deep external reference, which merits 5 under the simple-skill exception.

5 / 5

Total

18

/

20

Passed

Description

58%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.

The description names a specific, distinctive tool niche with several concrete capabilities, but it entirely lacks trigger guidance and leans on tool-specific jargon ("sync freshness", "Gitcrawl repo work") instead of natural user phrasing. Adding an explicit "Use when..." clause with plain-language triggers would raise completeness and trigger term quality substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when searching GitHub issues/PRs offline, checking whether local GitHub data is stale, finding duplicate or related issues, or deciding whether to consult live GitHub."

Replace jargon-heavy phrases with natural terms: spell out "pull requests" alongside "PR", and reword "sync freshness" as "checking whether the local archive is stale".

Clarify "Gitcrawl repo work" into a concrete action (e.g. "developing the Gitcrawl repository itself") so the last capability is as specific as the others.

DimensionReasoningScore

Specificity

Names several concrete capabilities ("issue/PR search, sync freshness, duplicate clusters, current GitHub handoff") though "Gitcrawl repo work" is generic, leaving minor gaps in coverage rather than the comprehensive coverage of a 5.

4 / 5

Completeness

The "what" is clear (GitHub archive search, sync, duplicate clustering, handoff), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant keywords like "GitHub", "issue/PR search", and "duplicate clusters" are present, but common natural phrasings users would actually say ("find duplicate issues", "stale GitHub data", "pull requests") are missing and "sync freshness" is tool jargon.

3 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (local GitHub archives, duplicate clusters, Gitcrawl-specific work) distinct from generic GitHub skills, with only minor overlap risk from the vague "current GitHub handoff" and "Gitcrawl repo work" phrases.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openclaw/openclaw

Path

.agents/skills/gitcrawl/SKILL.md

Reviewed

Table of Contents

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.