CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-verification-gate

Use when about to declare work complete, fixed, passing, or done

Quality

63%

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/skill-verification-gate/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 verification workflow itself is exemplary — a crisp gated procedure with explicit checkpoints, evidence tables, and red-green feedback loops. Weaknesses concentrate in bundle hygiene and focus: dead references to nonexistent files, a cryptic jargon-heavy opening section, near-duplicate rationalization/red-flag tables, and niche Octopus tooling mixed into the portable core.

Suggestions

Fix or remove dead references: 'skills/blocks/codex-host-adapter.md' and the Integration-with-Other-Skills file list point to files not present in the bundle.

Merge the Rationalization Table and Red Flags table, which restate the same excuses, and move the Claude Octopus/orchestrate.sh specifics into a separate reference file so SKILL.md stays host-neutral.

Rewrite the 'Portable feature evidence' section in concrete terms or drop it — 'policy provenance', 'open-marker count', and 'task-contract digest' are ungrounded jargon with no actionable instruction.

DimensionReasoningScore

Conciseness

The core sections (The Gate, Evidence table, Examples) are tight and table-driven with no concept explanation, but the Rationalization Table and Red Flags table duplicate each other almost point-for-point ('I'm confident this works' and the subagent claim appear in both), and the Claude Octopus/orchestrate.sh sections are niche context that pads length. This is 'mostly efficient but includes some unnecessary content that could be tightened' (anchor 3), not anchor 4's 'minor instances'.

3 / 5

Actionability

The Gate gives an executable 5-step procedure, the Evidence table maps each claim type to its required output, the examples show concrete command output, and the bash snippets for synthesis verification are copy-paste ready. It falls short of anchor 5 because the 'Portable feature evidence' section ('policy provenance', 'open-marker count', 'task-contract digest') is abstract jargon with no executable guidance, and general-case verification commands are only described generically.

4 / 5

Workflow Clarity

The Gate is a clear 5-step sequence with an explicit validation checkpoint (step 4 'VERIFY — Does output actually confirm the claim?'), the Red Flags table acts as a stop-and-check checklist, and the regression example lays out a full red-green feedback loop with recovery steps. This matches anchor 5 ('clear sequence with explicit validation steps; feedback loops for error recovery; checklists') — appropriate for a skill whose entire purpose is validation.

5 / 5

Progressive Disclosure

The single-file body has clear section headers, but it references files that do not exist in the bundle ('skills/blocks/codex-host-adapter.md', flow-develop.md, skill-code-review.md, etc.) and inlines niche host-specific and Octopus-specific content that belongs in a separate reference file. Broken references plus inline-able content matches anchor 3 ('references present but not clearly signaled; content that should be separate is inline') rather than anchor 4's 'minor organization gaps'.

3 / 5

Total

15

/

20

Passed

Description

40%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 a pure trigger clause: it captures a genuinely useful activation moment with natural phrasing, but completely omits what the skill does. Users and the model cannot distinguish it from any other end-of-task skill. Adding the core capability (e.g., requiring fresh verification evidence before completion claims) would lift both the what/when completeness and distinctiveness.

Suggestions

Add a 'what' clause before the 'Use when' clause, e.g., 'Enforces a verification gate requiring fresh command evidence before any completion claim. Use when about to declare work complete, fixed, passing, or done.'

Include natural trigger synonyms such as 'tests pass', 'works', 'verified', or 'ready to ship' to broaden keyword coverage.

Sharpen distinctiveness by scoping the trigger away from every task ending, e.g., 'before claiming work is done or reporting results' paired with the verification capability.

DimensionReasoningScore

Specificity

The description names its domain ("declare work complete, fixed, passing, or done") but states zero concrete actions — the skill's actual capability (verifying claims with fresh evidence) is entirely absent. This matches anchor 2 ('Names the domain but actions are minimal or generic') better than anchor 1 because the trigger moment is concretely phrased rather than pure abstraction.

2 / 5

Completeness

Only the 'when' is present ("Use when about to declare work complete, fixed, passing, or done") with no 'what' at all — exactly anchor 2's pattern ('only when is present without what'). It cannot score 3 because there is no clear 'what', and cannot score 4/5 which require both elements.

2 / 5

Trigger Term Quality

"complete", "fixed", "passing", and "done" are natural phrases users say when this skill applies. It falls short of anchor 5 because common variations like "works", "verified", "green", or "success" are missing, but coverage is better than anchor 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The trigger fires at the completion moment of virtually any engineering task, creating high overlap risk with any skill that activates at task end (commit, review, delivery skills). This is anchor 2 ('Very broad; high overlap risk with many similar skills') rather than anchor 1, since it is at least tied to a specific situation rather than being generically applicable.

2 / 5

Total

10

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

nyldn/claude-octopus

Path

skills/skill-verification-gate/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.