CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-verify

Use when a nontrivial change needs end-to-end verification before committing or shipping

64

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/skill-verify/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 a highly actionable, well-sequenced verification gate with concrete commands and explicit validation checkpoints; its only real weakness is mild redundancy and some host/project-specific flavor that could be trimmed.

Suggestions

De-duplicate the Iron Law — keep either the <HARD-GATE> block or the code block, not both — to tighten conciseness.

Consider moving the Claude Octopus / orchestrate.sh specifics into a referenced file or trimming them so the core gate stays host-agnostic and leaner.

Verify the cross-referenced paths (e.g., skills/blocks/codex-host-adapter.md, flow-develop.md) resolve in the target host, since no bundle files are present here.

DimensionReasoningScore

Conciseness

The body is mostly tight checklists and tables that assume Claude's competence, but it repeats the Iron Law twice (once in a <HARD-GATE> block and once in a code block) and carries project-specific Claude Octopus/orchestrate.sh flavor, fitting the 'mostly efficient but could be tightened' anchor rather than the lean level 3.

2 / 3

Actionability

It gives concrete executable commands ("npm test", "ls -la ~/.claude-octopus/results/*-synthesis-*.md | tail -1", "wc -l ...") plus explicit evidence criteria in tables and copy-paste bash snippets, matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The Gate is a clearly sequenced IDENTIFY → RUN → READ → VERIFY → ONLY THEN flow with explicit validation checkpoints ('check exit code, count failures', 'Does output actually confirm the claim?') and a red-green-red-green regression example with feedback loops, matching the level-3 anchor.

3 / 3

Progressive Disclosure

It is a single self-contained file with well-organized sections (Iron Law, The Gate, What Counts as Evidence, Red Flags, When to Apply, Examples) and no nested/deep references; with no bundle files needed, the simple-skill scoring note allows level 3 for well-organized sections.

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 has an explicit and well-timed 'Use when…' trigger that clearly answers both what and when, but its action list is thin and it shares the verification niche with several sibling skills, creating overlap risk.

Suggestions

Lead with one or two concrete verification actions before the trigger (e.g., 'Run the test/build command and read its output to confirm a change is safe. Use when…') to lift specificity toward level 3.

Add common user phrasings to the trigger (e.g., 'before committing, pushing, or shipping') to broaden trigger-term coverage.

Sharpen distinctiveness by naming the gating moment more uniquely (e.g., 'end-to-end verification gate') to reduce overlap with code-review and TDD skills.

DimensionReasoningScore

Specificity

Quotes "end-to-end verification" and "committing or shipping" — it names the domain and a couple of actions but does not enumerate multiple concrete verification actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.

2 / 3

Completeness

The explicit "Use when a nontrivial change needs end-to-end verification before committing or shipping" provides both a stated action (end-to-end verification) and an explicit 'Use when…' trigger, satisfying the level-3 'clearly answers both what AND when with explicit triggers' anchor; it is not level 2 because the trigger clause is present rather than merely implied.

3 / 3

Trigger Term Quality

Includes natural terms like "verification", "committing", and "shipping", but is missing common variations users would say (e.g., 'tests pass', 'before I push', 'build', 'lint'), fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The 'before committing or shipping' gating moment gives it a niche, but verification broadly overlaps with sibling skills the body itself cites (skill-code-review, skill-tdd), matching the 'somewhat specific but could still overlap with similar skills' anchor rather than a conflict-free level 3.

2 / 3

Total

9

/

12

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
nyldn/claude-octopus
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.