CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-autoresearch

Karpathy-style bounded keep-or-revert loop for creating or improving one skill at a time. Use when the user wants to create a new skill or improve an existing one through fixed eval batches, a results ledger, baseline comparisons, and controlled promotion instead of a one-shot draft.

Quality

84%

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

77%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 well-engineered process skill: the loop is clearly sequenced with strong validation checkpoints and crash-triage feedback loops, and the guidance is mostly copy-paste actionable. Its main weaknesses are a dangling 'templates/' reference inlined into a monolithic body and repeated restatements of the simplicity criterion.

Suggestions

Create the referenced 'templates/' bundle files (experiment-brief.md, results.tsv schema) and move the inline templates and TSV examples out of SKILL.md, replacing them with one-level-deep references — this fixes both the dangling reference and the monolithic structure.

State the simplicity criterion once (in the Keep-or-Revert phase) and drop the duplicating paragraphs in Purpose and Rules to cut roughly 20 lines of redundant instruction.

Add one concrete worked example of an eval prompt with its 0-1 rubric row so the scoring procedure in 'How to score an eval run' is fully reproducible.

DimensionReasoningScore

Conciseness

The body is efficient and imperative throughout, assuming Claude's competence with no padded concept explanations. The simplicity criterion is stated three times (Purpose, Phase 5, Rules), which is trimmable repetition and keeps it below the lean anchor 5.

4 / 5

Actionability

Concrete, executable guidance dominates: exact workspace layout, a 10-field brief checklist, per-prompt scoring steps, keep/discard/crash decision rules, and a full TSV schema with example rows. It falls short of anchor 5 because 'Use the templates in `templates/`' points to a nonexistent directory and eval prompts/rubrics remain placeholders.

4 / 5

Workflow Clarity

Seven clearly sequenced phases with explicit validation checkpoints: baseline capture before editing, identical eval batch and rubric per iteration, recorded scores in the ledger, and a crash-triage feedback loop with revert-to-last-winner recovery and bounded stop conditions. This matches the level-5 anchor.

5 / 5

Progressive Disclosure

The skill is a single monolithic file with no bundle files; the experiment-brief template and TSV schema (exactly the material the referenced 'templates/' directory should hold) are inlined, and the 'templates/' reference is dangling since no such files exist in the bundle. This matches anchor 3 — some structure, but content that should be separate is inline.

3 / 5

Total

16

/

20

Passed

Description

83%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 mechanisms, an explicit 'Use when' trigger clause, and a distinctive niche. Its only weaknesses are slightly jargon-tinged framing ('Karpathy-style', 'controlled promotion') and a few missing natural trigger synonyms like 'benchmark' or 'validate'.

DimensionReasoningScore

Specificity

The description lists several specific concrete mechanisms — 'keep-or-revert loop', 'fixed eval batches, a results ledger, baseline comparisons, and controlled promotion' — going beyond 1-2 actions. It falls short of level 5 because the items are mechanism labels rather than comprehensive coverage of distinct capability operations.

4 / 5

Completeness

It explicitly answers 'what' (a bounded keep-or-revert loop with eval batches, a results ledger, baseline comparisons, and controlled promotion) and 'when' ('Use when the user wants to create a new skill or improve an existing one through fixed eval batches'), matching the level-5 anchor exactly.

5 / 5

Trigger Term Quality

Natural user phrases like 'create a new skill' and 'improve an existing one' are present, giving good keyword coverage. A few natural terms users would say ('benchmark', 'test', 'validate', 'iterate') are missing, so it does not reach comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — empirically improving one skill via a measured loop — with triggers unlikely to fire for unrelated skills. There is minor overlap risk with a generic skill-creation skill ('create a new skill'), keeping it below level 5.

4 / 5

Total

17

/

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

0xRabbidfly/Eric-Cartman

Path

.github/skills/skill-autoresearch/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.