CtrlK
BlogDocsLog inGet started
Tessl Logo

gate-check

Advisor-checked decision gates. Freezes a drafted option set, has an independent external advisor rule it genuine / collapsed / malformed, then verifies the cited grounds before it reaches the user.

48

Quality

51%

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

Fix and improve this skill with Tessl

tessl review fix ./epistemic-cooperative/skills/gate-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%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 defines a rigorously sequenced, well-validated workflow, but it is delivered as an unusually verbose monolith whose abstract prose blunts actionability and leaves no room for progressive disclosure into reference files.

Suggestions

Move the Advisor Interface internals, record-lifecycle detail, and the restating Rules section into reference files (e.g., references/advisor-interface.md, references/record-lifecycle.md) and keep SKILL.md a lean overview.

Tighten the prose into imperative steps and tables, cutting the nested-clause rationale that re-derives why each guard exists; assume Claude's competence.

Add concrete execution specifics for the underspecified steps — the substrate-anchor capture, the per-invocation path naming, and the `codex exec` invocation — so the guidance is copy-paste ready.

DimensionReasoningScore

Conciseness

The ~5300-word body is noticeably verbose, with elaborate nested-clause rationale ('a count kept in two places drifts in one of them', 'Authorship does not transfer across a filter') padding most sections; it does not assume Claude can infer intent.

2 / 5

Actionability

Structured guidance is present — the four-in/four-out dispatch spec, the Phase 3 disposition table, and the Phase 2 verification checklist — but it is expressed in dense abstract prose with execution gaps (e.g., how exactly to capture the substrate anchor or name the per-invocation path) rather than crisp executable steps.

3 / 5

Workflow Clarity

A clear Phase 0–4 sequence with an explicit verification phase, feedback loops (re-anchor once, single rebuild recheck), and an Error Handling table; the dense prose and self-referential Rules section introduce minor clarity gaps that keep it below 5.

4 / 5

Progressive Disclosure

Section headers are well organized, but the skill is a 258-line monolith with no bundle files (references/scripts/assets absent) and detail that could live in separate files — the record-lifecycle and Advisor Interface internals, the largely restating Rules section — is inlined.

3 / 5

Total

12

/

20

Passed

Description

55%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 specific and occupies a clearly distinct niche, but it leans on skill-specific jargon for its triggers and omits any explicit 'when to use' guidance, capping completeness.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g., 'Use when a drafted decision keeps feeling like a choice but every option leads to the same place, or when it is unclear whether options are genuinely different').

Soften the jargon with everyday synonyms alongside 'genuine / collapsed / malformed' (e.g., 'real choice', 'options that converge', 'wrong axis') so users can recognize the trigger.

DimensionReasoningScore

Specificity

Names several concrete actions — 'Freezes a drafted option set', 'has an independent external advisor rule it genuine / collapsed / malformed', 'verifies the cited grounds' — listing the three verdicts explicitly; minor gaps in coverage keep it just below a 5.

4 / 5

Completeness

The 'what' is clear (freeze, adjudicate, verify), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Terms like 'decision gates', 'option set', and 'genuine / collapsed / malformed' are the skill's own jargon rather than the natural phrases a user would say when reaching for it, with no everyday synonyms present.

2 / 5

Distinctiveness Conflict Risk

The 'advisor-checked decision gates' niche and its verdict vocabulary are highly distinctive, with minimal risk of triggering for an unrelated skill.

5 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.