fdr

Keep track of Chatto's features as Feature Decision Records (FDRs) — one structured document per feature capturing behavior, design decisions, and rationale. Replaces the older agent-docs/features/ system.

Quality

67%

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/fdr/SKILL.md

Quality

Content

77%

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

The body is highly actionable with concrete templates, paths, and sequenced workflows backed by validation checkpoints and an audit feedback loop. Its main weaknesses are repeated anti-implementation guidance that could be consolidated and a lack of file-based progressive disclosure for a fairly long skill.

Suggestions

Consolidate the three places that warn against implementation details ('What an FDR Is NOT', the 'going too deep' callout, and 'Writing Style') into a single 'Scope' or 'What an FDR is NOT' section to remove redundancy.

Move the FDR template, TOC format, and/or verification checklist into a references/ file (e.g. references/TEMPLATE.md) and link to it from SKILL.md to improve progressive disclosure.

Tighten the 'Writing Style' section so it cross-references the anti-implementation rule once rather than restating it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what markdown or decision records are), but the anti-implementation message is repeated across three sections ('What an FDR Is NOT', the 'going too deep' callout, and 'Writing Style'), so it could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: the file naming pattern 'FDR-{NNN}-{kebab-case-slug}.md', a full FDR template, a TOC format, exact paths like 'cli/internal/core/permissions.go', and invocation examples like '/fdr new voice-calls'.	3 / 3
Workflow Clarity	Multi-step workflows (creating, updating, retiring) are explicitly sequenced, the audit process has a verification feedback loop (subagent verifies claims, returns a structured report), and a verification checklist plus a user-approval gate provide explicit validation checkpoints for destructive/batch operations.	3 / 3
Progressive Disclosure	The single 190-line SKILL.md is well-sectioned with a clear overview and no nested references, but no bundle files exist and the full template, verification checklist, and TOC format are inline content that could be split into reference files; at over 50 lines the simple-skill exemption does not apply.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 what an FDR is and is well-scoped to a distinct niche, but it lacks any 'Use when...' trigger guidance and leans on project-specific jargon, leaving a user unsure when to invoke it. Specificity is decent but action-oriented verbs are thin.

Suggestions

Append an explicit trigger clause, e.g. 'Use when managing, creating, or auditing Chatto feature documentation, or when the user mentions FDRs or feature design decisions.'

Add concrete action verbs (create, update, audit, retire FDRs) so the description lists multiple specific actions rather than only 'Keep track'.

Include a couple of natural user-facing trigger variations ('feature docs', 'feature decisions') alongside the FDR jargon.

Dimension	Reasoning	Score
Specificity	Names the domain ('Feature Decision Records (FDRs)') and concrete capture targets ('behavior, design decisions, and rationale'), but the only action verb is 'Keep track' — it does not list multiple distinct actions (create, update, audit, retire) the skill performs.	2 / 3
Completeness	It clearly answers 'what' (one structured document per feature capturing behavior, design decisions, and rationale) but provides no 'Use when...' clause or equivalent trigger guidance, so 'when' is missing and completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Contains some relevant natural terms ('features', 'design decisions', 'rationale', 'FDRs') but 'Feature Decision Records' is project-specific jargon and the description omits common variations and any explicit trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	Scoped to 'Chatto's features' with a distinct FDR framing and an explicit note that it 'Replaces the older agent-docs/features/ system', giving it a clear niche unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: chattocorp/chatto
Path: .agents/skills/fdr/SKILL.md
Commit: 65f65c3

Reviewed: 5 days 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.