CtrlK
BlogDocsLog inGet started
Tessl Logo

openclaw-github-repo-commander

7-stage super workflow for GitHub repo audit, cleanup, PR review, and competitor analysis

40

Quality

40%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/openclaw-github-repo-commander/SKILL.md

The canonical home for this skill is openclaw-github-repo-commander in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

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

This skill provides a reasonable high-level framework for a 7-stage GitHub repo audit workflow, but it lacks the concrete, executable guidance needed to be actionable. The referenced scripts and files (repo-audit.sh, pr_todo.json) are not included in the bundle, making the skill incomplete. The workflow stages describe what to do conceptually but not how to do it, and destructive operations in Stage 6 lack adequate validation checkpoints.

Suggestions

Include the actual `scripts/repo-audit.sh` script content or provide it as a bundle file, since the entire workflow depends on it.

Add concrete, executable commands or code for each stage — e.g., specific `gh` CLI commands for cloning, searching competitors, creating PRs, and pushing changes.

Add explicit validation checkpoints between stages, especially before and after Stage 6's destructive operations (e.g., 'List files to be deleted and confirm before proceeding').

Move detailed stage instructions into separate referenced files (e.g., STAGES.md) and keep SKILL.md as a concise overview with clear navigation links.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary padding ('turning a messy repo into a clean, well-documented, production-ready project') and explains concepts Claude would understand (what secrets patterns look like, what node_modules is). The 'When to Use This Skill' section is somewhat redundant. However, it's not egregiously verbose.

3 / 5

Actionability

The skill describes stages at a high level but provides almost no executable guidance. There's no actual code, no script contents, no concrete commands beyond mentioning `scripts/repo-audit.sh` and `gh` CLI. The examples show trigger phrases but not what Claude should actually do at each stage. The referenced `repo-audit.sh` script is never shown or included in the bundle.

2 / 5

Workflow Clarity

The 7 stages provide a clear sequence, and Stage 7 includes a validation step (re-run audit, target 7/7 PASS). However, there are no explicit feedback loops for error recovery, no validation checkpoints between intermediate stages, and the destructive operations in Stage 6 (deleting files, fixing security issues) lack explicit verification steps before proceeding. The destructive nature of Stage 6 without intermediate validation should cap this at 3.

3 / 5

Progressive Disclosure

No bundle files are provided despite references to `scripts/repo-audit.sh` and `pr_todo.json`. The skill references external scripts and files that don't exist in the bundle. All content is inlined in a single file with no clear pointers to supporting documentation. The stage descriptions are too thin to be self-contained yet don't reference detailed guides.

2 / 5

Total

10

/

20

Passed

Description

41%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 domain and several high-level actions but lacks concrete detail about what each stage involves and completely omits a 'when to use' clause. The term '7-stage super workflow' is marketing fluff that adds no discriminative value. The trigger terms are reasonable but incomplete, missing common synonyms and variations.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks to audit a GitHub repository, review pull requests, clean up repo issues, or compare against competitor repos'.

Replace '7-stage super workflow' with concrete action descriptions for each stage (e.g., 'checks CI status, reviews open PRs, identifies stale branches, analyzes dependency health').

Include natural synonyms and variations such as 'pull request', 'repository', 'code review', 'repo health check' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (GitHub repos) and lists several actions (audit, cleanup, PR review, competitor analysis), but they are high-level labels rather than concrete, detailed actions. The '7-stage super workflow' is vague branding rather than specificity.

3 / 5

Completeness

Provides a partial 'what' (audit, cleanup, PR review, competitor analysis) but has no 'when' clause at all. The absence of explicit trigger guidance caps this score. The description only tells what it does at a high level without specifying when Claude should select it.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'GitHub', 'repo', 'PR review', 'audit', and 'cleanup' that users might naturally say. However, it misses synonyms and variations like 'pull request', 'repository', 'code review', '.git', or 'repository health'.

3 / 5

Distinctiveness Conflict Risk

The combination of GitHub repo audit, cleanup, PR review, and competitor analysis is somewhat distinctive, but individual components like 'PR review' or 'cleanup' could easily overlap with other code review or repository management skills. The bundling of disparate tasks (competitor analysis alongside PR review) is unusual but not clearly delineated.

3 / 5

Total

11

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.