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.

63

Quality

76%

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 ./skills/delivery-gate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete install steps, configuration, and worked examples, and is well-organized as a self-contained skill; its main weakness is moderate verbosity in the rationale/analogy prose.

Suggestions

Tighten the 'Why' section by trimming the CI-pipeline analogy and the 'ship and forget' motivational line to keep only the failure-mode rationale.

Consider moving the configuration variable table and worked examples into a reference file once the skill grows, to keep the overview lean.

Drop the 'Quality' section's review-rounds claim unless it serves an actionable purpose; it reads as self-promotion rather than guidance.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and concrete examples, but the 'Why' section and CI-pipeline analogy add conceptual padding ('Over many sessions of ship and forget, the human hasn't grown') that could be tightened, fitting the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

Provides copy-paste install commands, a settings.json hook snippet, a configuration table with variables and defaults, and concrete examples with exact exit codes and stderr messages — fully executable and copy-paste ready.

3 / 3

Workflow Clarity

The check logic is sequenced clearly via the 'What It Checks' table and worked examples show the decision flow (edit_count -> complex -> LIBS check -> block/warn) with explicit validation feedback (exit codes and stderr), which is a clear sequence with explicit validation steps.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets are absent); the single self-contained SKILL.md is well organized into clearly labeled sections with a 'See Also' pointer to sibling skills, satisfying well-organized single-file structure with one-level navigation.

3 / 3

Total

11

/

12

Passed

Description

67%

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 distinct, with third-person voice and concrete actions, but lacks an explicit 'Use when...' trigger clause and leans on technical jargon over natural user terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a session involves complex multi-edit work that should capture learning, or when disk hygiene matters.'

Soften jargon ('filesystem mtime', 'Stop hook') with at least one natural user-facing phrase to improve trigger-term quality.

Lead with the highest-value trigger terms a user would actually say ('quality gate', 'learning capture', 'disk space') before the technical mechanism.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'blocks Claude from finishing', 'Detects rationalization patterns', 'stale learning logs (filesystem mtime)', and 'low disk space' — matching the anchor for several specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does, but there is no explicit 'Use when...' trigger clause; the 'when' is only implied by it being a Stop hook, so per the rubric guideline a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Terms like 'quality checks', 'learning logs', and 'disk space' are somewhat natural, but 'Stop hook', 'filesystem mtime', and 'self-audit' are technical jargon and common user phrasings are missing, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

It carves a clear niche (mechanical, deterministic session-hygiene gate) and explicitly distinguishes itself from self-audit, making conflict with other skills unlikely.

3 / 3

Total

10

/

12

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

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

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.