CtrlK
BlogDocsLog inGet started
Tessl Logo

research-refine-pipeline

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

65

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 ./skills/skills-codex/research-refine-pipeline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured orchestration skill: clear phased workflow with gate checkpoints, concrete templates, and one-level-deep references. Slight conciseness and verifiability gaps prevent top marks.

Suggestions

Tighten the Overview so it does not restate the frontmatter description, reclaiming tokens without losing information.

Make the Phase 0/Phase 2 validation checks explicitly checkable (e.g., a crisp pass/fail condition) to push workflow clarity toward a 5.

Where sibling skills or shared protocols are referenced, confirm those paths resolve in the bundle so progressive disclosure can be verified against actual files.

DimensionReasoningScore

Conciseness

Mostly lean bullet/phase structure that assumes Claude's competence; the Overview lightly re-states the frontmatter description and a few list items could be trimmed, so it sits just below the lean 5.

4 / 5

Actionability

Concrete default outputs, explicit gate-check questions, and a copy-ready PIPELINE_SUMMARY.md template plus present-summary block give actionable guidance; core refinement logic is deferred to sibling skills, leaving minor gaps.

4 / 5

Workflow Clarity

Phases 0–5 are clearly sequenced with explicit checkpoints (Phase 0 triage, Phase 2 Planning Gate) and decision branches; not a destructive/batch operation so no cap applies, but validation is qualitative rather than command-driven.

4 / 5

Progressive Disclosure

The overview points one level deep to sibling skills and shared protocols, clearly signaled ("read these sibling skills only when needed"); no local bundle files exist to verify, and references are external relative paths, keeping it just below a 5.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description: concrete actions, explicit what-and-when with varied trigger phrases, and a clear niche. The only soft spot is minor overlap with the two component skills it composes.

DimensionReasoningScore

Specificity

Names concrete actions ("chains `research-refine` and `experiment-plan`", produces "focused final proposal plus detailed experiment roadmap") — several specific actions with minor coverage gaps, not the fully comprehensive list of a 5.

4 / 5

Completeness

Explicitly states both what it does (end-to-end chained workflow yielding proposal + experiment roadmap) and when to use it, with concrete trigger phrases — fully matches the 5 anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases ("one-shot pipeline", "build a pipeline", "do it end-to-end", "generate both the method and experiment plan together", plus the Chinese synonym "串起来") — good coverage with a few common variations absent.

4 / 5

Distinctiveness Conflict Risk

Carves a clear integrated-pipeline niche distinct from its components, but because it composes two sibling skills there is minor overlap risk with `research-refine` and `experiment-plan` individually.

4 / 5

Total

17

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
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.