CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fdr

Keep track of product or project features as Feature Decision Records (FDRs): one structured document per feature capturing behavior, design decisions, and rationale.

Quality

79%

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/fdr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

This is a strong, highly actionable instruction-only skill: concrete templates, naming conventions, sequenced workflows with validation checkpoints, and a clear audit protocol with user-approval gating. Its only real weakness is mild redundancy — the anti-implementation-detail rule and some checklist items repeat guidance already given elsewhere.

DimensionReasoningScore

Conciseness

The body is prescriptive and lean — it never explains concepts Claude already knows and uses tight, directive prose ("No function signatures, no wire-format dumps... Stop and pull back to behavior and rationale"). Minor redundancy keeps it from anchor 5: the no-implementation-details rule is stated three times ("What an FDR Is NOT", "Writing Style", "Verification Checklist") and checklist items restate workflow steps.

4 / 5

Actionability

Everything is executable for an instruction-only skill: an exact file-naming pattern (FDR-{NNN}-{kebab-case-slug}.md), a complete copy-paste markdown template with per-section guidance, enumerated status values with when to use each, a concrete TOC table format, and numbered step-by-step procedures for every mode. This matches anchor 5's fully concrete, copy-paste-ready bar.

5 / 5

Workflow Clarity

Create, update, retire, and audit workflows are each clearly sequenced with explicit checkpoints: the audit process verifies every claim category (gates, behavioral claims, design decisions, related records), returns a structured report (Verified/Discrepancies/Stale/Missing), and only applies updates with user approval. A verification checklist and parallel-audit guidance round out anchor 5's explicit validation and feedback-loop criteria.

5 / 5

Progressive Disclosure

The single SKILL.md is well organized with clear sections and no buried or nested references, and no bundle files exist to evaluate. It sits at anchor 4 rather than 5 because at ~215 lines some self-contained material (the FDR template plus status values, and the TOC format) could be split into a reference file, though nothing is misfiled or hard to navigate.

4 / 5

Total

18

/

20

Passed

Description

61%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 distinctive, clearly defining what an FDR is and what each document contains, but it entirely lacks a "when to use" trigger clause and under-sells the skill's actual operations (creating, updating, auditing FDRs). It reads as a definition rather than an invocation trigger.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to document, update, or audit product features, or mentions FDRs, feature docs, or feature design decisions."

Enumerate the concrete actions the skill performs (create FDRs, update them as features evolve, audit FDRs against the codebase) instead of the single 'keep track of' verb.

Include natural synonyms users might say, such as 'feature documentation' or 'document a feature', to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ("Feature Decision Records (FDRs)") and one concrete action ("Keep track of product or project features") with what each document captures ("behavior, design decisions, and rationale"), but it does not enumerate the skill's actual capabilities (create, update, audit FDRs). This matches anchor 3 (domain plus 1-2 concrete actions) rather than anchor 4, which expects several specific listed actions.

3 / 5

Completeness

The "what" is clear (keep track of features as structured per-feature documents capturing behavior, decisions, rationale), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not score 2 because the "what" half is specific and concrete.

3 / 5

Trigger Term Quality

Natural terms like "features", "product", "design decisions", "rationale", and "FDRs" give good keyword coverage a user would plausibly say. It falls short of anchor 5 because common phrasings such as "feature documentation", "document a feature", or "feature docs" are absent, but it is well above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

"Feature Decision Records (FDRs)" is a clear niche with distinct terminology, making accidental triggering by generic documentation requests unlikely. Minor overlap risk remains with ADR/architecture-doc skills, which the description does not explicitly distinguish, so anchor 4 fits better than anchor 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

chattocorp/chatto

Path

.agents/skills/fdr/SKILL.md

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.