CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verification-before-completion

Review and validate completion claims. Use when you are about to say work is complete, fixed, passing, pushed, or ready for review.

Quality

77%

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/agent-ops/verification-before-completion/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A disciplined, security-conscious instruction skill with a clear sequenced workflow, explicit fail-fast gates, and good section hygiene. It loses points on actionability (abstract directives with no concrete commands or worked examples) and on progressive disclosure, where every cross-file reference points to nonexistent paths while the actual reference files go unmentioned.

Suggestions

Add one concrete worked example: an exact command rerun (e.g., `npm test --silent`), the resulting evidence, and before/after final claim wording showing narrowed language when evidence is partial.

Fix the Progressive Disclosure section to reference the real bundle files (references/contract.yaml, references/evals.yaml, references/task-profile.json) instead of nonexistent `Infrastructure/references/...` paths.

Merge the redundant Validation section into the Workflow (steps 4-5 already state the same gates) and clarify or drop the unexplained "Schema-bound outputs include `schema_version`" line.

DimensionReasoningScore

Conciseness

The body is lean: short bullet sections like "## Inputs" and "## Gotchas" ("A previous pass does not prove the current head is green") with no explanations of concepts Claude already knows, matching anchor 4's "efficient; minor instances that could be trimmed". It is not 5 because of redundancy — "## Validation" repeats workflow steps 4-5, and the cryptic "Schema-bound outputs include `schema_version`" earns no clarity for its tokens.

4 / 5

Actionability

Guidance is directional but abstract: "Run the narrowest real validator or command path available" and "Inspect 2-3 focused surfaces" give no concrete commands, worked example, or sample output (e.g., what a "verification checklist" or narrowed "final claim wording" actually looks like). This matches anchor 3 ("some concrete guidance but incomplete... missing key details") for an instruction-only skill; it is not 2 because the workflow, failure mode, and example invocations do constrain behavior.

3 / 5

Workflow Clarity

The 5-step workflow has explicit checkpoints and a feedback loop — "Stop at the first failed gate" and "Rerun the relevant validation after fixes before claiming completion" — matching anchor 4's clear sequence with most checkpoints present. It falls short of anchor 5 because the steps are abstract (no concrete commands or checklist artifacts), unlike anchor 5's fully specified validate/fix/re-validate examples.

4 / 5

Progressive Disclosure

The body is well-sectioned and signals deferred loading ("Load only the specific archived file needed for the current task"), but scored against the actual bundle the navigation is broken: the referenced paths `Infrastructure/references/software-literature-expert-lens-pack.md` and `Infrastructure/references/deferred-skill-context/agent-ops-verification-before-completion/` do not exist, while the real bundle files (references/contract.yaml, evals.yaml, task-profile.json) are never referenced. This matches anchor 3 (structure present, references present but not correctly signaled) rather than 2, since the in-body organization itself is good.

3 / 5

Total

14

/

20

Passed

Description

81%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 well-structured description with excellent trigger-term coverage and an explicit what+when structure. Its main flaws are generic action verbs (review/validate) instead of concrete verification behaviors and second-person phrasing in the trigger clause, which the rubric penalizes.

Suggestions

Rewrite the trigger clause in third/impersonal person (e.g., "Use when about to report work as complete, fixed, passing, pushed, or ready for review") to remove the second-person "you are about to say".

Replace the generic verbs with concrete actions, e.g., "Rerun failing tests, check build/lint output, inspect changed files, and confirm evidence before claiming work is complete, fixed, passing, pushed, or ready for review."

Narrow the trigger slightly (e.g., "before reporting work as done") to reduce overlap with code-review and test-execution skills.

DimensionReasoningScore

Specificity

"Review and validate completion claims" names the domain with two actions, matching anchor 3, but the actions are generic verbs with no concrete verification steps (e.g., rerun failing tests, check CI, inspect the diff). Additionally, the trigger clause uses second person ("Use when you are about to say"), which the judging guidelines penalize by reducing specificity by 1, landing at 2.

2 / 5

Completeness

It explicitly answers both questions: "Review and validate completion claims" (what) and "Use when you are about to say work is complete, fixed, passing, pushed, or ready for review" (when) with concrete trigger phrases, exactly matching the anchor 5 good example's structure. It is not anchor 4 because the 'when' clause is already fully explicit and specific.

5 / 5

Trigger Term Quality

"complete, fixed, passing, pushed, or ready for review" comprehensively covers the natural phrases a user (or Claude's own internal state) would use when this skill applies, including synonyms for completion states. It is not merely technical jargon, and no common variations for this domain are conspicuously missing, matching anchor 5 rather than anchor 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

The niche (validating completion claims before reporting) is mostly distinct with clear triggers, but "ready for review" and "passing" create minor overlap with code-review and test-execution skills, matching anchor 4 ("minor overlap risk with closely related skills") rather than anchor 5's minimal conflict risk.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/verification-before-completion/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.