CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

repo-docs

Bootstrap or extend a repo's documentation for coding agents. Creates AGENTS.md + docs/ structure (architecture, guidelines, product-specs with stable IDs and invariants). Use when the user asks to "document the project for coding agents", "set up agent docs", "add AGENTS.md", "create docs/ structure".

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 instruction-only skill body: lean tables instead of prose, a sequenced workflow with validation checkpoints and user-confirmation gates, and a measurable Definition of Done. Content is appropriately split into one-level-deep, well-signaled references.

DimensionReasoningScore

Conciseness

The body is ~85 lines of pure instruction with dense tables ("| `AGENTS.md` | the pitch, tech stack, 30-second architecture... | rationale, full specs |") and zero explanation of concepts Claude already knows; even the opening triad ("Every project area has one stable home") states layout invariants in three short sentences rather than padding.

5 / 5

Actionability

Instruction-only but fully concrete: explicit file ordering ("Write `invariants.md` first... and `AGENTS.md` last"), an executable lint command ("Run `prose-lint.py` on `AGENTS.md` and every file under `docs/`"), testable rules ("An internal name in a spec... is a defect"), and measurable size budgets ("`AGENTS.md` at most about 150 lines, each feature spec 5 to 15 items of 1 to 3 sentences").

5 / 5

Workflow Clarity

A clearly sequenced 5-step workflow with explicit validation (step 5: lint and "fix every finding", backed by the Definition-of-Done item "prose-lint.py reports no findings"), two user-confirmation checkpoints (steps 2 and 5), and an evidence-based checklist — the validate-fix loop for this batch file-creation skill is specified, matching the anchor-5 pattern.

5 / 5

Progressive Disclosure

The body is a true overview that delegates writing rules ("../../assets/writing.md"), skeletons ("templates/"), the spec format ("templates/product-specs-README.md"), and linting ("scripts/prose-lint.py") to clearly signaled, one-level-deep references with a "Read at" timing column; nothing that belongs in a separate file is inlined. Note: the referenced bundle files were not present in the review directory to verify existence, but the written structure fully matches the anchor.

5 / 5

Total

20

/

20

Passed

Description

92%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: concrete deliverables, third-person voice, and an explicit 'Use when...' clause with natural quoted trigger phrases. The only gap is synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

"Bootstrap or extend a repo's documentation" plus "Creates AGENTS.md + docs/ structure (architecture, guidelines, product-specs with stable IDs and invariants)" names multiple concrete deliverables covering both the create and extend paths, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

Explicitly answers both questions: the 'what' ("Creates AGENTS.md + docs/ structure... with stable IDs and invariants") and the 'when' ("Use when the user asks to..." with four concrete trigger phrases), mirroring the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Four natural quoted phrasings ("set up agent docs", "add AGENTS.md", "create docs/ structure") give good keyword coverage, but the 5 anchor requires comprehensive synonym coverage and common variants like "write documentation", "document the codebase", or "onboarding docs" are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is agent-facing repo documentation with stable spec IDs, and triggers like "add AGENTS.md" and "set up agent docs" are distinct from generic documentation or README-edit requests, giving minimal overlap risk with related skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

korya/swd-skills

Path

skills/repo-docs/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.