CtrlK
BlogDocsLog inGet started
Tessl Logo

debug-false-positive

Diagnose and fix a Fallow false positive or false negative through extraction, resolution, graph, analysis, reporting, and real-consumer verification.

66

Quality

78%

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 ./.agents/skills/debug-false-positive/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an efficient, well-sequenced debugging workflow with concrete commands and built-in validation. Its main weakness is that a couple of steps stay at the hint level and the error-recovery feedback loop is implicit rather than explicit.

Suggestions

Make the feedback loop explicit, e.g. after step 5 add 'If the regression test still passes without the fix, the reduction is incomplete — return to step 2.'

Add a concrete pointer for the high-level steps, e.g. name the command or subtool used to 'Reduce to a minimal fixture' and to 'Fix the earliest incorrect layer'.

Clarify what 'review with the affected surface reviewers' invokes (the exact command or surface list) so step 7 is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — seven terse numbered steps plus one guardrail sentence, with no concept explanation or padding, matching the score-5 'every token earns its place' anchor.

5 / 5

Actionability

Most steps give executable specifics ('--format json --quiet', cleared '.fallow/ cache', 'review' with surface reviewers), but steps like 'Fix the earliest incorrect layer' and 'Reduce to a minimal fixture' remain high-level hints, leaving minor gaps short of copy-paste readiness.

4 / 5

Workflow Clarity

The seven steps are clearly sequenced and include validation checkpoints (regression test in step 5, old-vs-new comparison in step 6), but the error-recovery feedback loop is only implicit rather than spelled out as a validate-fix-retry cycle, keeping it just below a 5.

4 / 5

Progressive Disclosure

This is a simple, single-purpose skill under 50 lines with no need for external references; the single well-organized section with a numbered list satisfies the rubric's simple-skill exception allowing a 5.

5 / 5

Total

18

/

20

Passed

Description

71%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 specific and action-rich with a clear niche, but it omits any explicit 'Use when' trigger guidance, which limits its completeness. Adding a usage trigger clause would lift the completeness score.

Suggestions

Append an explicit 'Use when ...' clause naming the trigger phrases users would say (e.g., 'Use when a Fallow scan reports a wrong result or when triaging a false positive/negative').

Include common synonyms or surface terms (e.g., 'scan result', 'misparsed finding') to broaden natural trigger coverage.

Tighten the distinctiveness by leading with the Fallow-specific trigger rather than the generic 'Diagnose and fix' phrasing.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'extraction, resolution, graph, analysis, reporting, and real-consumer verification' — giving comprehensive coverage of what the skill does, matching the score-5 anchor that lists several specific concrete actions.

5 / 5

Completeness

It clearly states the 'what' (diagnose and fix a false result via the listed stages) but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

It includes natural domain terms a user would say ('Fallow false positive', 'false negative', 'real-consumer verification'), giving good keyword coverage, but it lacks synonyms or common variations that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

The Fallow-specific framing ('Fallow false positive or false negative') carves a clear niche with minimal conflict risk, though the generic 'debug a false result' framing leaves minor overlap with general debugging skills rather than the fully distinct 5-anchor case.

4 / 5

Total

16

/

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
fallow-rs/fallow
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.