CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ds-scout

Use when a quest needs problem framing, literature scouting, dataset or metric clarification, or baseline discovery before deeper work.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ds-scout/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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, gated workflow protocol with genuinely concrete tool-call syntax, explicit stop/exit conditions, and clean one-level-deep references. Its main liability is substantial structural redundancy — exit criteria, memory rules, and stop rules are each restated two to three times across sections — inflating the body well beyond what the guidance requires.

Suggestions

Merge the duplicated exit criteria ('### 8. Stop on clarity, not exhaustion' and '## Exit criteria') into one section and state each rule once; the same applies to the memory-before-search rules given in 'Non-negotiable rules', '### 2.1', and 'Memory rules'.

Move detail-heavy schemas (paper-card metadata fields, search-ladder buckets, scouting ledger fields, baseline-scoring criteria) into the existing reference files so SKILL.md reads as an overview.

Define a concrete scale or rubric for the six baseline-candidate scoring criteria (e.g., high/medium/low with a decision rule) so the shortlist step is executable rather than judgment-only.

DimensionReasoningScore

Conciseness

The ~525-line body repeats whole rule clusters: exit criteria appear nearly verbatim in both '### 8. Stop on clarity, not exhaustion' and '## Exit criteria'; memory-search-before-web guidance is given three times (Non-negotiable rules, '### 2.1', 'Memory rules'); stop-search rules and template pointers are each stated twice. This is noticeably verbose with several padded/duplicated sections, though the padding is structural redundancy rather than explanations of concepts Claude already knows, keeping it above 1.

2 / 5

Actionability

Guidance is concrete for an instruction-only skill: exact tool calls with parameters (`memory.list_recent(scope='quest', limit=5)`, `artifact.arxiv(paper_id=..., full_text=False)`, `memory.write(...)` with a tags array example), named output files (`brief.md`, `artifacts/scout/*.md`), and template pointers for output shapes. It misses 5 because some directives stay abstract — baseline candidates must be 'scored' on six criteria with no scale or rubric defined, and the scouting ledger has no concrete format inline.

4 / 5

Workflow Clarity

The numbered workflow (reconstruct frame → identify unknowns → reuse memory → search neighborhood → eval contract → baseline shortlist → next anchor → update continuity) is clearly sequenced, with explicit checkpoints: a preconditions gate over `brief.md`/`plan.md`/`status.md`, per-search stop rules, an exit checklist, and a blocked-state error path with a structured 'ask the user' branch. It falls short of 5 because several checkpoints are implicit conditions rather than verifiable validation steps, and the durable writes have no verification step.

4 / 5

Progressive Disclosure

All four referenced files (`paper-triage-playbook.md`, `literature-scout-template.md`, `eval-contract-template.md`, `baseline-shortlist-template.md`) exist, are clearly signaled at the point of need, and are one level deep with no nested references (verified by grep). Good structure with clear section headers; it misses 5 because the SKILL.md body is a full 525-line protocol rather than an overview — detail like paper-card metadata lists and the search-ladder/ledger schemas would fit better in reference files.

4 / 5

Total

14

/

20

Passed

Description

75%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 solid trigger-style description that explicitly states when to use the skill and enumerates four concrete framing/scouting capabilities, all in appropriately concise third-person form. Its main weakness is that the what is only implied by the fused 'Use when...' clause, and it lacks common synonyms (papers, related work, benchmark) that would broaden natural trigger coverage.

Suggestions

Lead with a standalone what-statement (e.g., 'Frames research quests: clarifies task, evaluation contract, and baseline landscape.') before the 'Use when...' trigger clause so both what and when are explicitly separate.

Add natural synonyms users would say, such as 'related work', 'papers', 'benchmark', or 'SOTA lookup', to strengthen trigger-term coverage.

Narrow 'baseline discovery' to something like 'identifying candidate baselines' to reduce trigger overlap with a dedicated baseline skill.

DimensionReasoningScore

Specificity

"problem framing, literature scouting, dataset or metric clarification, or baseline discovery" lists several distinct, specific capabilities in the research-quest domain, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the actions are process-level abstractions rather than concrete operations, and above 3 because four concrete action areas are named, not just one or two.

4 / 5

Completeness

The "when" is fully explicit ("Use when a quest needs ... before deeper work") and the enumerated capabilities convey "what", but the two are fused into a single clause with no standalone what-statement, so it does not clearly match the 5 anchor's distinct what-AND-when structure. It is above 3 because the when-trigger is strong and the what is explicitly enumerated, not merely implied.

4 / 5

Trigger Term Quality

Natural domain keywords are present — "problem framing", "literature scouting", "dataset", "metric", "baseline discovery" — which a user of this research pipeline would plausibly say. It is below 5 because common synonyms like "related work", "papers", "benchmark", or "SOTA" are missing, and above 3 because keyword coverage spans all four facets of the stage rather than a couple of generic terms.

4 / 5

Distinctiveness Conflict Risk

"quest", "literature scouting", and "baseline discovery before deeper work" carve out a recognizable framing/scouting niche, but "baseline discovery" overlaps with the companion `baseline` stage skill, giving minor conflict risk with a closely related skill. It is well above 3 (not merely 'somewhat specific') and below 5 because that baseline overlap is real within a multi-stage skill suite.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (528 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

OpenLAIR/dr-claw

Path

skills/ds-scout/SKILL.md

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.