docs-research

Gather official, up-to-date documentation and convert it into a concise implementation checklist for the current coding task.

Quality

64%

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/docs-research/SKILL.md

Quality

Content

78%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 a tight, well-structured instruction-only skill that respects Claude's competence and stays on point. Its main weakness is actionability: the procedure is directional rather than executable, with no concrete commands, tools, or worked example. Workflow sequencing is clear with soft verification steps.

Suggestions

Add one concrete worked example (e.g., a short before/after showing a doc excerpt turned into a checklist with a citation) to lift actionability toward executable guidance.

Name the specific sources to prefer (e.g., official vendor docs, version-pinned package docs) and how to reach them (e.g., WebFetch on the official URL) so step 1 is actionable.

Add a small verification checkpoint, e.g. 'Confirm each checklist item maps to a cited constraint before finalizing.'

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a five-line numbered procedure plus a compact output format — with no padding or explanation of concepts Claude already knows, matching 'lean and efficient; assumes Claude's competence; every token earns its place'.	5 / 5
Actionability	Steps are concrete in intent ("Capture only task-relevant constraints (versions, limits, required fields, auth, edge cases)", defined output sections) but provide no executable commands, code, or specific tool invocations, fitting 'some concrete guidance but incomplete; missing key details'; not 4 because it stops at process direction rather than executable specifics.	3 / 5
Workflow Clarity	The five numbered steps give a clear sequence and the output format acts as a checklist, with soft checkpoints ("Cite where each critical constraint came from", "Call out unknowns explicitly") serving as verification; not 5 because there are no explicit validation/retry loops, though the task is non-destructive so the validation cap does not apply.	4 / 5
Progressive Disclosure	The skill is well under 50 lines with no need for external references and is cleanly organized into a procedure and an output-format section, so per the simple-skill guidance progressive disclosure scores 5 with well-organized sections.	5 / 5
	Total	17 / 20 Passed

Description

50%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 clear and concise about what the skill does but omits an explicit "Use when..." trigger clause, which caps completeness. Trigger term coverage is decent but lacks common natural variations. It is reasonably distinct from generic skills but could be more sharply differentiated.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs implementation guidance that depends on external/official documentation before writing code.'

Include natural trigger terms users would actually say such as 'docs', 'API reference', 'read the docs', or 'check the latest documentation'.

Tighten distinctiveness by naming the specific output (an implementation checklist with citations) so it is less likely to collide with general web-research skills.

Dimension	Reasoning	Score
Specificity	"Gather official, up-to-date documentation and convert it into a concise implementation checklist" names the domain and two concrete actions (gather docs, convert to checklist), matching the 'names domain and 1-2 concrete actions' anchor; not 4 because it does not list several specific actions with comprehensive coverage.	3 / 5
Completeness	It clearly states the "what" (gather docs, convert to checklist) but the "when" is only weakly implied by "for the current coding task" with no explicit "Use when..." clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords like "documentation" and "implementation checklist" are relevant but common natural variations ("docs", "API reference", file types) are absent, fitting 'some relevant keywords but missing common variations'; not 4 because coverage of natural phrases users would say is incomplete.	3 / 5
Distinctiveness Conflict Risk	"Gather official documentation and convert it into an implementation checklist" carves a somewhat specific niche but still overlaps with general research/lookup skills, matching 'somewhat specific but could still overlap with similar skills'; not 4 because the trigger is broad enough to risk overlap with adjacent skills.	3 / 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: JoseMD12/finance-hub
Path: .agents/skills/docs-research/SKILL.md
Commit: a8dbf2a

Reviewed: 3 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.