CtrlK
BlogDocsLog inGet started
Tessl Logo

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs — requires running verification commands and confirming output before making any success claims; evidence before assertions always

75

Quality

92%

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

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.

An actionable, well-structured discipline skill with a clear gated workflow and explicit validation checkpoints. Its main weakness is conciseness: the same verify-before-claiming principle is restated across several sections, inflating the token budget without adding new guidance.

Suggestions

Consolidate the redundant restatements of the core rule — the Iron Law block, the Gate Function preamble, and 'The Bottom Line' all say 'verify before claiming' — into one authoritative statement to cut repetition.

Merge or trim the Rationalization Prevention table, whose excuses (e.g. 'Should work now', 'Agent said success') largely duplicate the Red Flags list.

Consider trimming the Key Patterns section, since the Common Failures table already maps each claim type to its required evidence.

DimensionReasoningScore

Conciseness

It avoids explaining concepts Claude already knows, but restates the single core principle multiple times (the Iron Law, the Gate Function preamble, the Bottom Line, and the Rationalization Prevention table largely echo the Red Flags), so it is mostly efficient yet padded with repetition that could be tightened — the level 2 anchor.

2 / 3

Actionability

Gives concrete executable guidance: the 5-step Gate Function (IDENTIFY/RUN/READ/VERIFY/ONLY THEN) and the Common Failures table mapping each claim to specific required evidence (e.g. '0 failures', 'exit 0', 'VCS diff'), meeting the 'concrete, specific guidance' bar for an instruction-only skill.

3 / 3

Workflow Clarity

The Gate Function is a clearly sequenced multi-step process with an explicit validation checkpoint (step 4 VERIFY: 'Does output confirm the claim?') and a feedback branch ('If NO: State actual status with evidence'), matching the 'clear sequence with explicit validation steps and feedback loops' anchor.

3 / 3

Progressive Disclosure

No bundle files are needed and none exist; the single SKILL.md is broken into well-organized, navigable sections (Overview, Iron Law, Gate Function, Common Failures, Red Flags, Key Patterns, When To Apply) rather than a monolithic wall of text, satisfying the well-organized-sections criterion.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong description with an explicit 'Use when' trigger, concrete named actions, and a distinct niche; it clearly answers both what the skill does and when to apply it. Minor verbosity in the 'evidence before assertions always' tagline does not undermine clarity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'claim work is complete, fixed, or passing', 'committing or creating PRs', 'running verification commands', 'confirming output' — matching the 'multiple specific concrete actions' anchor rather than the vague 'Names domain and some actions' level 2.

3 / 3

Completeness

Explicitly answers both: what ('requires running verification commands and confirming output before making any success claims') and when ('Use when about to claim work is complete, fixed, or passing, before committing or creating PRs'), satisfying the explicit-trigger anchor for level 3.

3 / 3

Trigger Term Quality

Covers natural completion-related terms a user or context would surface — 'complete', 'fixed', 'passing', 'committing', 'creating PRs', 'success claims' — giving good coverage rather than the partial 'some relevant keywords' level 2.

3 / 3

Distinctiveness Conflict Risk

Targets a narrow behavioral niche (pre-claim verification) with distinct triggers unlikely to fire for tool-specific skills, matching the 'clear niche with distinct triggers' anchor rather than the overlapping level 2.

3 / 3

Total

12

/

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
darrenhinde/OpenAgentsControl
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.