CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-refine

Score and improve an artifact with a frozen rubric, independent models, implemented edits, and bounded rescoring

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-refine/SKILL.md

The canonical home for this skill is skill-refine in nyldn/claude-octopus

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 dense, safety-focused orchestration body with concrete commands, explicit budgets, strong validation checkpoints, and well-signaled on-demand phase resources. It falls short of top marks due to repeated invariants, script-invocation detail deferred to unverifiable reference files, and interleaved phase rules in the closing paragraphs.

Suggestions

Deduplicate the repeated invariants (secret inspection, "never reset counters", call-reservation rules) into a single checkpoint list referenced once per phase instead of restated across sections.

Include one minimal worked invocation of refinement-run.py begin/prepare and the single-judge refinement-pair.py adapter in the body so the core loop is executable before the phase files are loaded.

DimensionReasoningScore

Conciseness

The body explains nothing Claude already knows and is densely packed with operational rules, but invariants repeat: secret inspection appears twice ("inspect... for credentials and private tokens" and "inspect candidate, evidence and accessible context for secrets as required above") and "never reset counters" appears three times. This places it just below the 'every token earns its place' anchor, at 'minor instances... that could be trimmed'.

4 / 5

Actionability

Concrete material is present: a copy-paste bash block resolving OCTO_ROOT, exact commands ("preflight.sh --providers claude,codex"), exact phase resource paths, and numeric defaults (target 95/100, max five rounds, 30 minutes, 14 calls). It is not 5 because the actual invocation syntax for refinement-run.py and refinement-pair.py is deferred to the phase reference files, leaving minor executable gaps in the body itself.

4 / 5

Workflow Clarity

The five phases are numbered with explicit load points ("Load skills/skill-refine/references/phase-2.md" through phase-5.md) and validation is abundant ("Check remaining time and calls before every dispatch", "Stop after two rounds without verified improvement", "checking that the original has not changed since it was read"). It is not 5 because judging-contract, acceptance, resume, and delivery rules for phases 3-5 are interleaved out of sequence in the closing paragraphs, slightly muddying the end-to-end flow.

4 / 5

Progressive Disclosure

Phase detail is deferred to clearly signaled, one-level-deep resources loaded on demand ("Load only the next phase, and reload its resource after compaction"), which is well-structured. It is not 5 because the referenced files (references/phase-2.md..phase-5.md, scripts/refinement-*.py) are not present in this bundle to verify, and the paths resolve against the plugin root rather than the skill directory, complicating standalone navigation.

4 / 5

Total

16

/

20

Passed

Description

58%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 states a clear, multi-action 'what' with a distinctive multi-model rubric-based method, but it omits any 'when to use this' guidance and leans on workflow jargon rather than natural trigger terms. Completeness is capped at 3 by the missing trigger clause, and keyword coverage is only partial.

Suggestions

Add an explicit trigger clause, e.g. "Use when invoked via /octo:refine or when the user asks to score, review, or refine an artifact against a rubric."

Replace or gloss the process jargon ("frozen rubric", "bounded rescoring") with natural phrases users would actually say, such as "rubric-based scoring", "evaluate", and "iterative improvement".

Name the accepted artifact types (text, plans, code, documents, images) to sharpen specificity and improve trigger matching.

DimensionReasoningScore

Specificity

Phrases like "Score and improve an artifact" and "implemented edits, and bounded rescoring" list several concrete actions with mechanisms, matching the 'several specific actions; minor gaps in coverage' anchor. It is not 5 because "an artifact" leaves the object types (text, code, plans, images) unspecified, and not 3 because more than 1-2 concrete actions are named.

4 / 5

Completeness

The 'what' is clear ("Score and improve an artifact with a frozen rubric, independent models, implemented edits, and bounded rescoring") but the description contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is present and specific, not vague.

3 / 5

Trigger Term Quality

Terms like "frozen rubric", "independent models", and "bounded rescoring" are process jargon; only "score", "improve", and "rubric" are words a user would naturally say, and common variations ("refine", "evaluate", "review", "polish") are absent. This fits 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor.

3 / 5

Distinctiveness Conflict Risk

The method signature "frozen rubric, independent models, implemented edits, and bounded rescoring" carves a distinct niche unlikely to fire for unrelated skills, matching 'mostly distinct; minor overlap risk'. It is not 5 because without explicit triggers, the generic verbs "score and improve" could still overlap with general review or refinement skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

nyldn/claude-octopus

Path

.claude/skills/skill-refine/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.