inno-pipeline-planner

Guides the user through an interactive conversation to define their research project, then generates research_brief.json and tasks.json. Use when starting a new project, when no research_brief.json exists, when the user wants to start from a specific pipeline stage, or when the user wants to redefine their research pipeline.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body is well-structured and lean, with excellent progressive disclosure via a real reference bundle and a clear sequenced workflow. The main improvement area is adding an explicit output-validation/feedback step for the batch task-generation step.

Suggestions

Add an explicit validation/feedback loop after writing pipeline files (e.g., 'Validate research_brief.json and tasks.json against the schemas; if errors, fix and re-validate before summarizing') to strengthen the batch-generation checkpoint.

Tighten the 'Typical question buckets' and stage-determination lists into tighter bullets to push conciseness toward the lean anchor.

Consider a one-line 'quality gate' verification step in section 3 referencing the per-stage quality_gate fields before moving to the summary, making the validation explicit rather than implicit.

Dimension	Reasoning	Score
Conciseness	Lean, directive bullets that defer detail to reference files and avoid explaining concepts Claude already knows; a few sections (e.g., question buckets) could be trimmed slightly, keeping it just below the 'every token earns its place' anchor.	4 / 5
Actionability	Provides concrete file paths, an explicit stage order, generation rules, and sample user questions; as an instruction-only skill it is mostly executable, with the full JSON contracts intentionally deferred to reference files.	4 / 5
Workflow Clarity	Five clearly numbered steps with a summarize-and-confirm checkpoint (step 4) and non-negotiable guardrails; the only gap is an explicit validate/feedback loop on the generated JSON rather than a soft confirmation.	4 / 5
Progressive Disclosure	A short SKILL.md points to one-level-deep, well-signaled reference files (pipeline-contract.md index plus generation-rules, brief-schema, tasks-schema), all verified to exist, with clear navigation matching the top anchor.	5 / 5
	Total	17 / 20 Passed

Description

87%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 strong: it explicitly covers both what the skill does and when to use it, with concrete trigger conditions tied to distinctive pipeline artifacts. Minor headroom remains in specificity and trigger synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('define their research project', 'generates research_brief.json and tasks.json') with only minor gaps in coverage, fitting the 'lists several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Clearly states what it does (guides conversation, generates two JSON files) and gives an explicit 'Use when...' clause with multiple concrete trigger conditions, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-term coverage ('starting a new project', 'start from a specific pipeline stage', 'redefine their research pipeline') plus a concrete file name, but a few common synonyms a user might say are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (research pipeline planning) anchored to distinctive artifacts (research_brief.json, pipeline stage), minimizing overlap with other skills.	5 / 5
	Total	18 / 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: OpenLAIR/dr-claw
Path: skills/inno-pipeline-planner/SKILL.md
Commit: 4b35756

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.