setup-matt-pocock-skills

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Quality

92%

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

The canonical home for this skill is setup-matt-pocock-skills in mattpocock/skills

Quality

Content

85%Scale 1-3

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

This is a well-crafted prompt-driven skill with excellent workflow clarity and actionability. The 5-step interactive process is clearly sequenced with user confirmation checkpoints, specific file paths, and concrete decision trees. The main area for improvement is conciseness — the user-facing explainer blocks add length, though they serve a purpose in guiding non-technical users through unfamiliar concepts.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-structured but includes verbose explainer text blocks that are meant to be shown to the user. Some of the explanatory prose (e.g., describing what an issue tracker is, what triage labels are) could be more concise since Claude can generate contextual explanations on the fly. However, the verbosity is partially justified as these are user-facing explainers that the skill instructs Claude to present.	2 / 3
Actionability	The skill provides highly concrete, step-by-step guidance: specific commands to run (`git remote -v`), specific files to check, exact markdown block templates to write, specific file paths for output (`docs/agents/issue-tracker.md`), and references to seed template files. The decision tree for which file to edit (CLAUDE.md vs AGENTS.md) is explicit with clear rules.	3 / 3
Workflow Clarity	The 5-step process (Explore → Present → Confirm → Write → Done) is clearly sequenced with explicit checkpoints: present findings and get user confirmation before proceeding, show draft and let user edit before writing, walk through decisions one at a time. The workflow includes validation via user confirmation at steps 2 and 3, and has clear rules for edge cases (file already exists, section already exists, neither file exists).	3 / 3
Progressive Disclosure	The skill references seed template files (issue-tracker-github.md, issue-tracker-gitlab.md, etc.) as one-level-deep references, keeping the main SKILL.md focused on the process rather than inlining template content. The structure is well-organized with clear sections and the output files (docs/agents/*.md) are clearly signaled. Note: bundle files were listed as not provided, but the skill references them clearly by relative path.	3 / 3
	Total	11 / 12 Passed

Description

100%Scale 1-3

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

This is an excellent skill description that clearly communicates what it does (sets up agent configuration blocks and directories), when to use it (before first use of specific named skills or when those skills lack context), and uses highly specific trigger terms. It uses proper third-person voice and provides enough detail to be unambiguously distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: sets up an '## Agent skills' block in AGENTS.md/CLAUDE.md, creates 'docs/agents/' directory, configures issue tracker type, triage label vocabulary, and domain doc layout. Very concrete about what it produces.	3 / 3
Completeness	Clearly answers both 'what' (sets up Agent skills block, docs/agents/ directory with issue tracker, triage labels, and domain doc layout) and 'when' (explicitly states 'Run before first use of [list of skills]' and 'if those skills appear to be missing context about...'). The 'when' clause is explicit and actionable.	3 / 3
Trigger Term Quality	Includes highly specific natural trigger terms: names the exact skills it supports ('to-issues', 'to-prd', 'triage', 'diagnose', 'tdd', 'improve-codebase-architecture', 'zoom-out'), mentions 'AGENTS.md', 'CLAUDE.md', 'issue tracker', 'GitHub', 'triage labels', 'domain docs'. These are terms users would naturally reference.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — targets a very specific niche of configuring agent skill context in AGENTS.md/CLAUDE.md files. The named skills, file paths, and setup-oriented purpose make it clearly distinguishable from the downstream skills it supports.	3 / 3
	Total	12 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: SnowingFox/ai-skills
Path: .cursor/skills/setup-matt-pocock-skills/SKILL.md
Commit: d6882ad

Reviewed: ~14 hours 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.