CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is a well-organized, lean instruction-only skill that uses progressive disclosure effectively with real, well-signaled reference files. Its main gaps are the absence of explicit validation checkpoints in the write-files step and some generation mechanics being deferred rather than shown inline.

Suggestions

Add an explicit validation checkpoint after writing the pipeline files (e.g., re-read research_brief.json and tasks.json to confirm they conform to brief-schema.md / tasks-schema.md before summarizing completion).

Show a minimal concrete example of the stage-to-task generation rule or a snippet of the expected JSON shape inline so the core mechanics are not entirely deferred to references.

Add a brief feedback loop for iteration requests (update -> verify consistency between brief and tasks.json) to match the validation rigor expected for batch file-generation workflows.

DimensionReasoningScore

Conciseness

Lean, directive prose ('Keep this file short', 'Read only what you need', 'Do not fabricate...') with no padding or explanation of concepts Claude already knows; every line is actionable guidance.

3 / 3

Actionability

Guidance is concrete and specific (exact file paths, stage order, JSON contracts via references) but the generation details are deferred to reference files rather than giving copy-paste-ready examples inline; it is an instruction-only skill so absence of code is not penalized, yet key generation mechanics are not shown directly.

2 / 3

Workflow Clarity

The five-step workflow is clearly sequenced with explicit decision branches (startStage selection, regenerate vs refine), but there are no explicit validation checkpoints confirming the generated JSON files conform before declaring done — risky for a file-generation operation.

2 / 3

Progressive Disclosure

SKILL.md is a concise overview that signals one-level-deep references (pipeline-contract.md index -> generation-rules.md / brief-schema.md / tasks-schema.md), and all referenced files exist in ./references/ with clear navigation.

3 / 3

Total

10

/

12

Passed

Description

100%

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 concise, written in third person, and clearly specifies both capabilities and explicit 'Use when' triggers tied to a distinct research-pipeline niche. It matches the high-quality anchor examples well.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Guides the user through an interactive conversation to define their research project', 'generates research_brief.json and tasks.json') with named deliverable artifacts rather than vague language.

3 / 3

Completeness

Clearly answers both 'what' (define project via conversation, generate research_brief.json and tasks.json) and 'when' with an explicit 'Use when...' clause enumerating four triggering conditions.

3 / 3

Trigger Term Quality

Natural user-facing trigger phrases are well covered ('starting a new project', 'no research_brief.json exists', 'wants to start from a specific pipeline stage', 'redefine their research pipeline') — terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Niche is clear and specific (Inno research pipeline planning with named JSON artifacts) with distinct triggers tied to research_brief.json existence, unlikely to conflict with unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenLAIR/dr-claw
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.