paper-experiment-stub

Demo-only stub experiment for meta-paper-write: generates a deterministic results.csv seeded by topic hash. Not real science.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/bundled/paper-experiment-stub/SKILL.md

Quality

Content

73%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 concise, well-structured overview for a simple bundled skill, correctly offloading executable logic to its script. Its weakness is that the body itself offers no executable example or explicit pointer to the script, leaning entirely on the frontmatter entrypoint for actionability.

Suggestions

Add a one-line executable example mirroring the entrypoint, e.g. `python scripts/gen_results.py --topic "..." --out paper/results.csv`, so the body is copy-paste actionable.

Add an explicit in-body pointer to the bundled script (e.g. 'See scripts/gen_results.py') to strengthen the progressive-disclosure navigation.

Optionally note the deterministic re-run guarantee as a short bullet so users know outputs are stable across runs.

Dimension	Reasoning	Score
Conciseness	The body is a lean 4-sentence overview that assumes Claude's competence and states only what is non-obvious (columns, seeding behavior); every token earns its place with no padding or over-explanation.	5 / 5
Actionability	It describes the inputs and outputs concretely (topic phrase -> 20-row CSV with named columns, SHA-256 seeding) but contains no executable code or commands in the body itself; the executable detail lives in the bundled script rather than inline.	3 / 5
Workflow Clarity	For a simple single-purpose skill the single action is unambiguous, and the entrypoint (command, args, timeout) in the frontmatter sequences execution clearly; it is not a destructive/batch operation requiring validation, so the cap does not apply, though no explicit checkpoints exist.	4 / 5
Progressive Disclosure	Structure is appropriate: a concise overview in the body with the real logic correctly split into the bundled scripts/gen_results.py (verified to exist), referenced via the frontmatter entrypoint; minor gap is the lack of an explicit in-body pointer to the script.	4 / 5
	Total	16 / 20 Passed

Description

60%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 concrete and honest about being a demo stub, with a specific action and clear niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause and reliance on a meta-skill name rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when running the meta-paper-write demo and a placeholder results.csv is needed.'

Replace reliance on the meta-skill name with natural user-facing trigger phrases such as 'demo experiment', 'placeholder results', or 'stub CSV'.

Mention the .csv extension and the deterministic/stable-re-run property as natural keywords to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('generates a deterministic results.csv seeded by topic hash') plus its scope ('Demo-only stub experiment for meta-paper-write'), which is several specific details, though it lists only one real action with minor gaps in coverage.	4 / 5
Completeness	It clearly states what it does, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	It includes relevant terms ('experiment', 'results.csv', 'topic hash') but is framed around a meta-skill name ('meta-paper-write') rather than natural phrases a user would actually say, and lacks synonyms or file-extension triggers.	3 / 5
Distinctiveness Conflict Risk	The 'meta-paper-write' scope and 'Not real science' framing make it mostly distinct with a clear niche; minor overlap risk with general experiment/CSV skills, but the explicit stub/demo framing narrows conflict.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/paper-experiment-stub/SKILL.md
Commit: 94ac35e

Reviewed: 4 days 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.