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.

60

Quality

70%

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

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, well-organized debug workflow that respects token budget and is appropriately scoped for a simple skill. Its main weakness is actionability — several steps name what to do without giving the executable command — and the absence of explicit error-recovery feedback loops after fixing.

Suggestions

Add the concrete commands for the verification steps, e.g., the exact invocation to clear `.fallow/` and diff old vs. new output, so steps 1 and 6 are copy-paste ready.

Insert an explicit feedback loop after the fix, e.g., "If the regression test still fails, return to step 3 and re-trace the next incorrect layer" to satisfy the error-recovery expectation for a code-fixing workflow.

DimensionReasoningScore

Conciseness

The body is lean and instruction-dense with no padding or explanation of concepts Claude already knows; every line is a concrete directive, matching the "every token earns its place" anchor.

3 / 3

Actionability

It gives concrete guidance — exact flags ("--format json --quiet"), named pipeline layers (extract, resolve, graph, reachability), and specific verification steps — but most steps lack copy-paste-ready commands (e.g., the exact binary invocation for clearing `.fallow/` and comparing output), landing on "some concrete guidance but incomplete."

2 / 3

Workflow Clarity

The seven steps are clearly sequenced and include validation checkpoints (regression test that fails without the fix, real-consumer comparison), but there is no explicit error-recovery feedback loop (e.g., "if the regression test still fails, re-trace from step 3"), which the rubric expects for a destructive code-fixing workflow.

2 / 3

Progressive Disclosure

This is a short, single-purpose skill under 50 lines with no need for external references; its tight heading plus numbered list is well-organized and clear, which the simple-skills scoring note permits to score 3.

3 / 3

Total

10

/

12

Passed

Description

67%Weight 40%Scale 1-3

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 occupies a distinct niche, but it omits any explicit "Use when..." trigger guidance, which caps completeness. Trigger-term coverage is relevant but lacks common user phrasings.

Suggestions

Add an explicit "Use when..." clause naming the user phrasings that should trigger this skill (e.g., "Use when Fallow reports a wrong result, a false positive, or a missed finding").

Broaden trigger terms to include everyday phrasings a user might say ("wrong result", "missed bug", "incorrect finding") alongside "false positive" and "false negative".

DimensionReasoningScore

Specificity

It names the domain ("Fallow false positive or false negative") and lists multiple specific concrete actions — "extraction, resolution, graph, analysis, reporting, and real-consumer verification" — matching the anchor for listing multiple specific actions.

3 / 3

Completeness

It clearly states what the skill does (diagnose and fix) but lacks any "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

"false positive" and "false negative" are natural terms a user would say, but common variations a user might phrase differently (e.g., "wrong result", "missed bug", "incorrect report") are missing, so it lands on "some relevant keywords but missing common variations" rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

It targets a clear niche — Fallow false positive/negative debugging — with distinct triggers tied to a specific product, making it unlikely to fire for the wrong skill.

3 / 3

Total

10

/

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
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.