CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

doc-gardening

Find docs and agent instructions in the carnival that no longer match the code, and file one GitHub issue per stale doc. Use when running the doc gardening maintenance loop, or when asked to check whether the README, AGENTS.md, a game's README or a skill is out of date. Files issues only; never changes code or docs.

80

Quality

100%

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

The canonical home for this skill is doc-gardening in sjmaple/carnival

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.

The body is a tight, fully actionable instruction set: it enumerates exactly which docs to audit and what claim types to verify, specifies the issue title and body format with a worked example, and includes validation checkpoints (duplicate check, command verification, done-when criteria) plus graceful empty-result handling. It contains no filler, no over-explanation, and needs no external files at this size.

DimensionReasoningScore

Conciseness

The ~35-line body has no padding or general-concept explanation: the short intro carries non-inferable project facts ("Agents read these docs before they work", "the factory ships the fixes"), and the "What to check" / "What to file" sections are entirely task-specific. Every token earns its place, matching the lean-and-efficient anchor rather than the minor-over-explanation 4 anchor.

5 / 5

Actionability

Guidance is fully concrete and copy-paste ready: the title template "Docs: <file> is out of date", a line-pointer example "src/games/water-cannon/game.ts:12", per-doc-type check lists with specifics ("shot counts, speeds, points", "URL parameters, keys"), and a concrete "Done when" tied to "npm run check". As an instruction-only skill this matches the fully-executable top anchor; there is no pseudocode or vague direction.

5 / 5

Workflow Clarity

A clear two-phase sequence (audit each doc's claims, then file) with explicit validation checkpoints for a batch operation: duplicate guard ("Before filing, check the open issues and skip any doc that already has one"), command verification ("Run commands like npm run check if you need to confirm one works"), and the edge case "Nothing found is a fine result. Say so, and file nothing." The batch-operation cap does not apply because verification steps are present, so this matches the top anchor rather than the minor-validation-gaps 4 anchor.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed and no bundle files present; the two well-organized sections ("What to check", "What to file") plus a brief purpose intro satisfy the simple-skill criterion for the top score. The paths it cites (README.md, AGENTS.md, src/games/<game-id>/README.md, SKILL.md) are audit targets in the repo, not skill bundle references, so there are no dangling or buried references.

5 / 5

Total

20

/

20

Passed

Description

100%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 is exemplary: it states concrete capabilities with an explicit read-only/issue-filing boundary, and gives an explicit "Use when" clause with natural trigger phrases naming the exact doc types it covers. It clearly and compactly answers both what the skill does and when to invoke it, with no padding or over-claims.

DimensionReasoningScore

Specificity

Concrete actions are explicit: "Find docs and agent instructions in the carnival that no longer match the code", "file one GitHub issue per stale doc", plus the boundary "Files issues only; never changes code or docs" and the named target set (README, AGENTS.md, game READMEs, skills). This matches the anchor for multiple specific concrete actions with comprehensive coverage; it is not the 4 anchor because there are no minor gaps — actions, granularity, and boundaries are all stated.

5 / 5

Completeness

Explicitly answers both what ("Find docs... that no longer match the code, and file one GitHub issue per stale doc. Files issues only; never changes code or docs") and when ("Use when running the doc gardening maintenance loop, or when asked to check whether the README, AGENTS.md, a game's README or a skill is out of date") with concrete trigger phrases — a direct match to the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases are all present: "out of date", "stale doc", "doc gardening maintenance loop", and concrete targets "README", "AGENTS.md", "a game's README or a skill". Synonyms (stale / out of date) and file names are both covered, matching the comprehensive-synonyms anchor rather than the "a few natural terms missing" 4 anchor.

5 / 5

Distinctiveness Conflict Risk

"Files issues only; never changes code or docs" cleanly separates it from doc-fixing, doc-writing, and code-review skills, and the triggers ("doc gardening maintenance loop", "check whether the README... is out of date") are niche-specific with minimal conflict risk, matching the clear-niche anchor.

5 / 5

Total

20

/

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

guypod/carnival-factory-lab-20261022

Path

tessl-factory/skills/doc-gardening/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.