skill-verify

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

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-verify/SKILL.md

Quality

Content

88%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 a strong, actionable verification gate with excellent workflow sequencing and concrete commands and examples. Its main weaknesses are minor redundancy between the two excuse tables and several dangling cross-references to files that are not present in the bundle.

Suggestions

Consolidate the Rationalization Table and Red Flags table, which overlap heavily, into a single table to trim redundant tokens.

Resolve or remove dangling cross-references (codex-host-adapter.md, flow-*.md, skill-*.md) since no references/ bundle directory exists.

Consider moving the Claude Octopus / orchestrate.sh specifics into a separate reference file so the core gate stays lean for non-orchestration users.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-scannable via tables, but the Rationalization Table and Red Flags table overlap heavily (e.g. "I'm confident this works" / "It's a small change" appear in both) and a few concepts are restated across sections.	4 / 5
Actionability	Provides concrete executable guidance: a 5-step gate, copy-paste shell commands (ls -la, wc -l on synthesis files), and worked examples (test output with "Tests: 2 passed, 2 total" and a 4-step red-green-red-green regression loop) covering common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (IDENTIFY→RUN→READ→VERIFY→ONLY THEN) with an explicit hard validation checkpoint, plus a full feedback loop in the regression example and per-phase verification checkpoints for orchestrate.sh.	5 / 5
Progressive Disclosure	Well-organized into clear sections with no bundle files, but cross-references like `skills/blocks/codex-host-adapter.md` and the trailing `flow-.md`/`skill-.md` files do not exist as bundle files, and some multi-provider/orchestrate content that could be split remains inline.	4 / 5
	Total	18 / 20 Passed

Description

70%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 has a strong, explicit trigger clause and a clear niche, but under-specifies the concrete actions the skill performs, leaving the "what" thinner than the "when." It is concise and non-generic, which is a strength.

Suggestions

Add one concrete action clause stating what the skill does, e.g. "Runs fresh verification commands and requires passing evidence before allowing completion claims."

Include a couple of natural synonyms (e.g. "testing", "QA", "did it pass") alongside "verification" to broaden trigger coverage.

Consider naming the specific checkpoints it enforces (tests, build, regression) to lift specificity from a situational description to a concrete capability list.

Dimension	Reasoning	Score
Specificity	Names the domain ("end-to-end verification") and a concrete action context ("before committing or shipping"), but describes the triggering situation rather than listing multiple concrete actions the skill performs.	3 / 5
Completeness	Has an explicit, crisp "Use when..." clause; the "what" (end-to-end verification) is present but only weakly stated as a capability rather than spelled out as concrete actions.	4 / 5
Trigger Term Quality	Natural trigger phrasing ("Use when a nontrivial change needs...") with relevant keywords (verification, committing, shipping, end-to-end), though synonyms like testing/QA/did-it-pass are absent.	4 / 5
Distinctiveness Conflict Risk	The verification-gating niche with a "before committing or shipping" trigger is mostly distinct, with only minor overlap risk against general testing/review skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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-verify/SKILL.md
Commit: 242e51d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.