CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

readme-harvest

Skill di raccolta e indicizzazione documentazione sui README. Usa gofainder per ricerca, nocodaigo per esplosione/catalogazione, godocai per generazione skill/docs. Loop autodeterminato con meta-dev-kicker.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skill/readme-harvest/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

A compact, well-structured pipeline skill with mostly copy-paste-ready commands for three of its four phases. Its main weaknesses are the completely unvalidated batch workflow (no checkpoints between harvesting, explosion, and generation) and the command-less cataloging phase.

Suggestions

Add validation checkpoints after each phase, e.g. verify snippet output of nocodaigo ('controlla snippets/ non vuoto'), confirm INDICE_KB.md entries were added, and sanity-check generated skill/agent files before the loop re-runs.

Provide a concrete command or file format for Fase 2 (how to save sources into kb/ subdirectories and how INDICE_KB.md entries should be structured) instead of just listing target paths.

Specify loop parameters for meta-dev-kicker (interval, stop conditions) and what 'always updated' means in practice (e.g., diff against previous index) so the autonomous re-run is verifiable.

DimensionReasoningScore

Conciseness

The body is lean: bullet lists, short concrete commands, no explanation of concepts Claude already knows; only minor trimming opportunities (the ASCII pipeline repeats the phase order, and the intro sentence restates the title).

4 / 5

Actionability

Most phases give concrete, executable commands with realistic arguments ('gofainder search "GitHub README best practices"', 'nocodaigo explode ... --no-llm -o snippets/', 'godocai scan -d ...'), but Fase 2 provides only destination directories and 'Aggiorna index/INDICE_KB.md' with no command or format, leaving a minor gap.

4 / 5

Workflow Clarity

The four phases are clearly sequenced with a pipeline diagram, but there are no validation or verification checkpoints anywhere (e.g., confirming snippets were produced, the index updated, or generated skills are valid) in what is a batch pipeline auto-re-run on a schedule by meta-dev-kicker, which caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and is organized into clean per-phase sections with a pipeline overview, satisfying the simple-skill case for progressive disclosure.

5 / 5

Total

16

/

20

Passed

Description

53%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 communicates a recognizable niche (README knowledge harvesting) and its tool chain, but reads as internal shorthand: heavy proprietary jargon, no plain-language capability statement beyond generic verbs, and no 'use when' trigger clause. It would rarely be selected by a user phrasing a request in natural language.

Suggestions

Add an explicit trigger clause, e.g. 'Usa quando l'utente chiede di raccogliere/aggiornare documentazione sui README, indicizzare la KB, o rigenerare skill e agenti readmago'.

Translate tool names into concrete capabilities in the description (e.g. 'ricerca multi-engine ed estrazione contenuti', 'esplosione in snippet', 'generazione di skill/agenti') so the what is understandable without knowing the internal tools.

Include natural synonyms users would actually say (README, documentazione, best practices, KB, esempio README) to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain ('raccolta e indicizzazione documentazione sui README') and a few actions ('ricerca', 'esplosione/catalogazione', 'generazione skill/docs'), but the actions are generic verbs attached to opaque internal tool names (gofainder, nocodaigo, godocai), so coverage of what the skill concretely does remains partial.

3 / 5

Completeness

The 'what' is reasonably clear (collect, index, and transform README documentation into skills/agents), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'README' and 'documentazione' are relevant keywords a user might say, but the description is dominated by proprietary jargon (gofainder, nocodaigo, godocai, meta-dev-kicker) and lacks natural trigger phrases or synonyms like 'raccogli docs', 'aggiorna la KB', 'best practices README'.

3 / 5

Distinctiveness Conflict Risk

README documentation harvesting is a clear niche with minor overlap risk against general documentation or web-search skills; however, without explicit trigger phrases it does not reach the minimal-conflict bar of a 5.

4 / 5

Total

13

/

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

biodoia/readmago

Path

skill/readme-harvest/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.