CtrlK
BlogDocsLog inGet started
Tessl Logo

verification-before-completion

Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work state.

59

Quality

69%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/verification-before-completion/SKILL.md

The canonical home for this skill is verification-before-completion in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 content is a well-structured, actionable discipline skill with a clear gated workflow and explicit validation checkpoints, held back only by repetitive sections that inflate length without adding guidance.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but redundancy pads it: a duplicate 'When to Use' section appears twice, 'The Bottom Line' restates the overview, and the 'Rationalization Prevention' table overlaps the 'Red Flags' list, matching the 'mostly efficient but could be tightened' anchor rather than the lean 4-anchor.

3 / 5

Actionability

The Gate Function is a concrete 5-step procedure (IDENTIFY/RUN/READ/VERIFY/CLAIM) and the Common Failures table plus ✅/❌ Key Patterns give specific, executable behavioral guidance; not a 5 because, as an instruction-only skill, it stops short of fully copy-paste-ready artifacts.

4 / 5

Workflow Clarity

The Gate Function is a clearly sequenced workflow with an explicit verification checkpoint (step 4) and a feedback loop (If NO: state actual status with evidence), matching the top anchor; the skill is itself about validation so no destructive/batch cap applies.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is well-organized into clearly headed sections (Iron Law, Gate Function, Common Failures, Key Patterns), but at ~135 lines with some redundant sections it sits at 'good structure, minor organization gaps' rather than the ideal 5.

4 / 5

Total

16

/

20

Passed

Description

65%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 well-triggered with an explicit, forceful 'Use when' clause and clear domain framing, but it front-loads a moralizing principle instead of concrete capabilities, slightly weakening specificity and distinctiveness.

Suggestions

Lead with what the skill does ('Forces fresh verification evidence before any completion or success claim') before the principle, to add concrete action language and raise specificity.

Tighten the over-broad trigger 'ANY positive statement about work state' to concrete wording examples (e.g. 'Done', 'All tests pass', 'Looks good') to reduce over-trigger risk.

Add 1-2 concrete capability phrases (e.g. 'runs the relevant verification command, reads full output, and reports status with evidence') so the 'what' is actionable rather than purely a principle.

DimensionReasoningScore

Specificity

The description names the domain ('verification before completion') but lists no concrete capabilities or actions — it states a principle ('Claiming work is complete without verification is dishonesty') rather than what the skill does, matching the 'names the domain, actions minimal or generic' anchor and falling below the 3-anchor which requires 1-2 concrete actions.

2 / 5

Completeness

It has both a 'what' (the verification-before-claims principle) and an explicit 'when' ('Use when ANY variation of success/completion claims...'), but the 'what' is an abstract principle rather than a concrete capability, so it sits at 4 rather than the fully concrete 5-anchor.

4 / 5

Trigger Term Quality

Phrases like 'ANY variation of success/completion claims', 'ANY expression of satisfaction', and 'ANY positive statement about work state' give good, natural trigger coverage with synonym variations; not a 5 because it lacks the exhaustive enumeration of specific completion-wording variants a user might say.

4 / 5

Distinctiveness Conflict Risk

The verification-before-completion niche is mostly distinct from task-specific skills, but the very broad trigger 'ANY positive statement about work state' creates minor over-trigger/overlap risk with other meta-discipline skills, keeping it just below 5.

4 / 5

Total

14

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.