conformance-loop

Iteratively improve Fallow analysis accuracy by comparing it with competing tools and verified source truth across a stable real-world corpus.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/conformance-loop/SKILL.md

Quality

Content

71%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 an exceptionally lean, well-sequenced workflow with built-in verification checkpoints appropriate to a batch/validation process. Its main weakness is actionability: several steps give high-level direction without the concrete commands or specifics needed to execute them directly.

Suggestions

Add concrete invocations for running Fallow and comparison tools (e.g., the exact CLI commands and how to align settings), so steps 2 and 6 are executable without inference.

Specify where the stable corpus and regression fixture live and what 'documented equivalent settings' concretely means, turning step 1 and step 5 from directives into actions.

Dimension	Reasoning	Score
Conciseness	The body is a lean 8-line numbered workflow with no padding and no explanation of concepts Claude already knows; even the closing line 'Competitor output is a lead, not ground truth.' earns its place as a non-obvious principle. Every token carries weight.	5 / 5
Actionability	Most steps are high-level directives ('Define the capability and stable project corpus', 'Run Fallow and comparison tools with documented equivalent settings') without executable specifics. Only step 4 (classification categories) and step 7 ('Run `review`') offer concrete detail, matching the anchor-2 'minimal concrete guidance; high-level hints' level rather than 3 which requires more executable detail.	2 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints: step 3 'Manually verify disagreements against source' and step 6 'retain only net improvements' form a feedback gate. It is not a 5 because there is no explicit error-recovery loop (fix-and-revalidate) spelled out.	4 / 5
Progressive Disclosure	This is a simple, single-purpose skill under 50 lines with no bundle files and no need for external references; the well-organized numbered list with a header meets the simple-skill exception for a 5. No nested or buried references exist.	5 / 5
	Total	16 / 20 Passed

Description

46%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 states a clear, specific purpose but omits any explicit trigger guidance, leaving the 'when to use' question unanswered. It is concise and distinct but would benefit from natural user-facing trigger terms and a 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when improving or validating Fallow's analysis accuracy against other tools or known-correct source.'

Include natural trigger phrases users would actually say, such as 'validate Fallow results', 'compare Fallow with other tools', or 'check Fallow accuracy'.

Dimension	Reasoning	Score
Specificity	Names the domain (Fallow analysis accuracy) and 1-2 concrete actions ('comparing it with competing tools', 'verified source truth'), but coverage is not comprehensive. It sits at the anchor-3 level rather than 4 because the actions are limited to comparison/verification with no broader action set.	3 / 5
Completeness	It clearly states what the skill does ('Iteratively improve Fallow analysis accuracy by comparing...') but provides no 'when' guidance — there is no 'Use when...' clause, which caps completeness at 3 per the rubric guideline. It is not a 4 because the 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	The terms ('Fallow analysis', 'competing tools', 'source truth', 'corpus') are domain jargon rather than the natural phrases a user would say. It is not a 1 because 'Fallow' is a recognizable keyword, but it lacks the common user-facing trigger phrasing.	2 / 5
Distinctiveness Conflict Risk	The Fallow-specific conformance-testing niche is mostly distinct with minor overlap risk against general analysis/validation skills. It is not a 5 because there are no explicit distinct trigger phrases that fully eliminate conflict risk.	4 / 5
	Total	12 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .agents/skills/conformance-loop/SKILL.md
Commit: cbd9cf4

Reviewed: about 6 hours ago

Table of Contents

Discovery Implementation Validation

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.