ds-full-pipeline

Full DeepScientist research pipeline: scout → baseline → idea → experiment → analysis → optimize → write → review → finalize. End-to-end autonomous research lifecycle.

Quality

76%

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 ./skills/ds-full-pipeline/SKILL.md

Quality

Content

85%

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-structured, actionable orchestration guide with concrete per-stage commands, explicit gates, and feedback loops; its main weakness is mild redundancy from restating the stage sequence in three forms.

Suggestions

Drop either the top arrow diagram or the bottom timeline table to remove the triplicated sequence restatement, keeping the timeline only if duration/autonomy columns add value.

Consider moving the per-stage Output lines into the referenced sub-skills if they duplicate what those skills already document.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with one-line stage descriptions and no concept explanations Claude already knows, but the sequence is conveyed three times (arrow diagram, per-stage sections, and the timeline table), so it could be tightened.	2 / 3
Actionability	Every stage gives a concrete, copy-paste-ready slash command (e.g. '/ds-scout "$ARGUMENTS"', '/ds-baseline') with explicit expected outputs, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 9 stages are clearly sequenced with explicit validation checkpoints (Gate 1, Gate 2), a review feedback loop ('fix and re-review, max 2 rounds'), and a fail-gracefully rule, satisfying the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	The SKILL.md is a lean overview that delegates detail to the individual /ds-* sub-skills (acting as one-level-deep references) with well-organized sections and easy navigation; no bundle files are needed or nested references present.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and distinctive, enumerating the full research pipeline stages, but it omits any explicit 'when to use' trigger guidance and relies on domain jargon rather than natural user keywords.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants an end-to-end autonomous research run or asks to run the full DeepScientist pipeline.'

Include natural-language keywords users would actually say (e.g. 'run a research study', 'full research workflow', 'automated paper writing') alongside the stage names.

Clarify when NOT to use it (e.g. single-stage tasks) to further reduce overlap with the individual /ds-* sub-skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline stages — 'scout → baseline → idea → experiment → analysis → optimize → write → review → finalize' — matching the anchor for enumerating several specific actions rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (the chained research stages) but provides no 'Use when...' clause or equivalent explicit 'when to use it' guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant terms like 'research pipeline' and 'research lifecycle', but these are domain-specific and lack common user variations; no natural trigger phrasing a user would spontaneously say, so it sits at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche as the DeepScientist end-to-end orchestrator with distinct stage-based triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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/ds-full-pipeline/SKILL.md
Commit: 6da7f7c

Reviewed: about 7 hours 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.