plan-prep

Research enterprise context before plan mode — surface design docs, similar implementations, stakeholders, and related systems before architecting or designing a feature.

Quality

69%

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 ./plugins/glean/skills/plan-prep/SKILL.md

Quality

Content

67%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 body delivers a well-structured, actionable 6-phase Glean workflow with concrete query templates, a vetting checkpoint, and a report template. It is somewhat padded in its rationale sections and the large report template could be split into a reference file for better progressive disclosure.

Suggestions

Trim the 'Why This Matters' bullets and the BE SKEPTICAL intro prose; the vetting table already conveys the criteria, improving token efficiency.

Move the Phase 6 report markdown template into a references/ file (e.g. REPORT_TEMPLATE.md) and link to it, advancing progressive disclosure toward a 5.

Add an explicit validate→fix→retry loop in Phase 5 (e.g. if findings are stale/tangential, re-query with refined terms before rejecting) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and query templates, but the 'Why This Matters' section and per-category bullets restate what the phases already demonstrate and could be trimmed; not a 4 due to that padded explanatory block.	3 / 5
Actionability	Provides concrete, copy-pasteable search-query templates ('search "[task] architecture OR design doc"'), a tool-selection table mapping needs to Glean tools, and a full report template; minor gaps keep it from a 5.	4 / 5
Workflow Clarity	Six phases are clearly sequenced with an explicit vetting/validation checkpoint (Phase 5: 'Vet All Research') before report generation, plus a 'If Limited Context Found' fallback; not a 5 because there is no tight validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	Single self-contained file with well-organized section headers and no nested references; not a 5 because the large inline report template (~Phase 6) could arguably live in a separate reference file, and the doc is fairly long for one file.	4 / 5
	Total	15 / 20 Passed

Description

58%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 clearly states what the skill does and surfaces a concrete set of enterprise-context targets, but lacks an explicit 'Use when...' trigger clause and natural trigger synonyms, which weakens completeness and trigger-term quality. It is mostly distinct from other skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to research enterprise context before entering plan mode, or says plan prep, prep for plan, or research before planning.'

Include more natural trigger synonyms and phrasings users would actually say (e.g. 'research before planning', 'prep for plan') directly in the description.

Tighten the action list toward comprehensive coverage (e.g. name the Glean tools used) to push specificity toward a 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Research enterprise context') and several concrete actions ('surface design docs, similar implementations, stakeholders, and related systems'); not a 5 because coverage of actions is broad but not fully enumerated.	4 / 5
Completeness	Has a clear 'what' (research/surface enterprise context) but the 'when' is only weakly implied via 'before plan mode' with no explicit 'Use when...' trigger clause, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Contains relevant natural terms ('plan mode', 'design docs', 'architecting or designing a feature') but misses common variations/synonyms a user might say (e.g. 'research before planning', 'prep for plan') that only appear in the body.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (enterprise context gathering before plan mode via Glean); minor overlap risk with general research skills keeps it just below a 5.	4 / 5
	Total	14 / 20 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	Warning

	Total	15 / 16 Passed

Repository: gleanwork/claude-plugins
Path: plugins/glean/skills/plan-prep/SKILL.md
Commit: a549de6

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.