CtrlK
BlogDocsLog inGet started
Tessl Logo

delivery-gate

Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass.

69

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

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.

The body is well-structured, actionable, and clear, with concrete examples and a clean decision table. The main gap is that the referenced implementation file quality-gate.py is not bundled, slightly weakening actionability and progressive disclosure.

Suggestions

Ship quality-gate.py in a scripts/ bundle so the 'cp quality-gate.py ~/.claude/scripts/' install step is actually executable.

Trim the 'Why' section and the CI-pipeline analogy to reduce token overhead without losing the core motivation.

Link the See Also entries (self-audit, verification-loop, gateguard) to their actual skill paths so the contrast is navigable rather than name-only.

DimensionReasoningScore

Conciseness

Mostly efficient with tight tables and concrete examples, but the 'Why' section and the CI-pipeline analogy add mild over-explanation that could be trimmed.

4 / 5

Actionability

Provides concrete install commands, a settings.json snippet, a configuration table, and exit-code examples, but references quality-gate.py which is not present in the bundle, leaving a gap in copy-paste readiness.

4 / 5

Workflow Clarity

The 'What It Checks' decision table plus the Examples section make the gate flow unambiguous; this is a single-purpose gate rather than a destructive/batch operation, so the 3-cap does not apply.

4 / 5

Progressive Disclosure

A single well-organized SKILL.md with clear sections and no nested references; however quality-gate.py is referenced as the implementation but is absent from the scripts/ bundle.

4 / 5

Total

16

/

20

Passed

Description

92%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, complete with an explicit trigger clause, and clearly differentiated from sibling skills. The only weakness is mild jargon mixed into otherwise natural trigger language.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'blocks Claude from finishing until quality checks pass', 'Detects rationalization patterns… stale learning logs (filesystem mtime), and low disk space' — covering all three checks comprehensively.

5 / 5

Completeness

Explicitly answers both what (a Stop hook detecting rationalization, stale learning logs, and low disk space) and when (a concrete 'Use when…' trigger phrase).

5 / 5

Trigger Term Quality

The 'Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass' clause is a natural trigger, but it is mixed with technical jargon ('filesystem mtime', 'regex') and lacks common synonyms.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (mechanical Stop-hook gate) and explicitly contrasts itself from self-audit and verification-loop, minimizing conflict risk.

5 / 5

Total

19

/

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
affaan-m/ECC
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.