CtrlK
BlogDocsLog inGet started
Tessl Logo

verify

Decide whether the diagnosed behaviour is actually a bug or the code doing what it was designed to do. This is the gate that guards the fix stage.

58

Quality

66%

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 ./infra/emdash-bot/.flue/skills/verify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured, actionable instruction-only skill with a clear sequenced procedure, concrete tooling, and defined verdicts. It is held below the top band only by minor conciseness padding and the lack of fully explicit in-workflow validation checkpoints.

Suggestions

Tighten the opening paragraph (e.g., 'Plenty of EmDash issues describe behaviour that is intentional but under-documented, surprising at first glance, or a misuse of the API.') to remove explanatory framing Claude already infers.

Add one explicit validation checkpoint in the procedure (e.g., a 'before emitting the verdict, confirm the cited path actually states the intent' step) to strengthen workflow_clarity.

Optionally inline one concrete 'bug vs intended-behavior vs unclear' mini-example with paths to make the verdict guidance fully copy-paste-ready.

DimensionReasoningScore

Conciseness

The body is largely efficient with a tight numbered procedure and concrete verdict examples, but minor explanatory padding such as 'Plenty of EmDash issues describe behaviour that is intentional but under-documented...' could be trimmed.

4 / 5

Actionability

Provides a concrete 7-step procedure, named inspection tools (read_file, ls, grep, code), named cross-reference docs (AGENTS.md, CONTRIBUTING.md, docs/), defined verdicts with worked examples, and an explicit output format; minor gaps keep it just below fully copy-paste-ready.

4 / 5

Workflow Clarity

Steps are clearly sequenced and step 6 ('Resist two failure modes') acts as a self-check/feedback loop; the skill is read-only so the destructive-operation cap does not apply, but explicit validation checkpoints within the flow are lighter than a 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, needs no external references, and is organized into clear sections (Environment, Do not, Procedure, Output), satisfying the simple-skill exception for a 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 clearly conveys the skill's purpose as a bug-vs-intent verdict gate but omits an explicit 'Use when...' trigger clause, capping completeness and trigger-term quality at 3. It is specific and reasonably distinct from sibling skills.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when deciding whether diagnosed behavior is a bug or intended, before running a fix').

Include a few synonyms users might say ('is this a bug', 'by design', 'intended behavior', 'false positive') to broaden trigger-term coverage.

Surface a second concrete action (e.g., 'cite the comment, doc, or test that establishes intent') to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain (bug vs. intended-behavior triage) and the concrete distinguishing action 'Decide whether the diagnosed behaviour is actually a bug or the code doing what it was designed to do', but lists only 1-2 actions rather than comprehensive coverage.

3 / 5

Completeness

Has a clear 'what' (decide bug vs intended), but 'when' is only weakly implied with no explicit 'Use when...' clause, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes relevant keywords like 'bug', 'behaviour', and 'fix stage', but lacks common synonyms/variations and a natural 'Use when...' phrasing users would actually say.

3 / 5

Distinctiveness Conflict Risk

Carves a clear niche as a verdict gate guarding the fix stage, with only minor overlap risk against general code-review or diagnosis skills; not a 5 because trigger phrasing is not explicit enough to fully minimize conflict.

4 / 5

Total

13

/

20

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
emdash-cms/emdash
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.