CtrlK
BlogDocsLog inGet started
Tessl Logo

formal-review

This skill should be used when the user asks to "formal review", "formal lens review", or invokes /formal-review. A fixed-lens PR review for this repository's formally-structured protocol changes: it pins a Category Theory / Type Theory / Operational Semantics lens panel over only the files changed in a PR, analyzes each lens in isolation, adversarially cross-verifies the findings, and posts the survivors as a single consolidated PR comment. Project-local contributor tooling.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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-structured, actionable review-pipeline skill with concrete commands and clear phase sequencing. Its main weakness is conciseness: the Rules section and project-rationale material duplicate content already covered in the phase descriptions.

Suggestions

Remove or fold the '## Rules' section into the phases — its nine rules restate the phase content (fixed panel, changed-files-only, isolated-then-adversarial, confidence ≥ 80%, verify-before-post, harness permission, single comment), cutting significant duplication.

Trim the '## Why this is a project skill' rationale and the repeated substrate self-justifications (e.g. 'declining /conduct here IS that warrant relaying'); these explain protocol internals Claude does not need to execute the review.

State the 'isolated → adversarial' mechanism and the 'fixed formal panel' once (in Phase 2) and reference it from the Pipeline Overview and Rules, instead of re-explaining it in all three places.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the '## Rules' section restates the phase descriptions and the 'Why this is a project skill' rationale plus substrate-meta jargon ('warrant relaying') add noticeable duplication that could be tightened.

3 / 5

Actionability

Provides concrete executable commands — 'gh pr diff {N}', 'git diff HEAD', 'gh pr view --json number', 'gh api repos/{owner}/{repo}/issues/{N}/comments --input -', 'jq --rawfile' — with only minor gaps (the jq/heredoc composition is not given as a single ready-to-run line).

4 / 5

Workflow Clarity

A clearly sequenced six-phase pipeline with explicit validation checkpoints (confidence ≥ 80% drop, adversarial refutation, Phase 3 direction-error guard, harness permission gate); the validation is partly relay/non-gating rather than a hard fix-and-retry loop, a minor gap below a 5.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized into clear sections (Why, Caller Signature, Pipeline Overview, When to Use, Phase 0–4, Rules) with no need for external references; the >50-line length and the redundant Rules section keep it just short of a 5.

4 / 5

Total

15

/

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.

A strong, third-person description that states concrete capabilities, explicit trigger phrases, and a well-scoped niche. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'pins a Category Theory / Type Theory / Operational Semantics lens panel', 'analyzes each lens in isolation', 'adversarially cross-verifies the findings', 'posts the survivors as a single consolidated PR comment' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (fixed-lens PR review that pins the formal triple and posts a single consolidated comment) and 'when' ('when the user asks to formal review, formal lens review, or invokes /formal-review') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural trigger phrases a user would actually say — 'formal review', 'formal lens review', and the '/formal-review' slash command — including synonyms and the invocation form.

5 / 5

Distinctiveness Conflict Risk

Scoped to 'this repository's formally-structured protocol changes' with distinct '/formal-review' / 'formal lens review' triggers, giving it a clear niche with minimal overlap against generic review skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jongwony/epistemic-protocols
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.