CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research

Creates evidence-tracked research reports and parallel AI-provider/mode studies with original outputs and source-level synthesis. Use for 帮我调研一下 / 深度研究 / 综述报告 / write a report, research reports, literature reviews, market/industry analysis, competitive landscapes, or multi-route ChatGPT/Kimi/UniFuncs research. For choosing technology use tech-selection; for competitor code analysis use competitors-analysis.

63

Quality

75%

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 ./deep-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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-engineered orchestration skill: explicit multi-phase pipeline, strong validation checkpoints, real degradation paths, and a verified, well-signaled one-level-deep reference bundle. Its main cost is redundancy — the Enterprise mode is documented twice and governance rules are restated — which inflates token load and slightly obscures the control flow.

Suggestions

Consolidate the duplicated Enterprise pipeline: remove the E1-E7 recap ("Enterprise Research Mode (Specialized Pipeline)" and the "E3-E7" summary) and keep one authoritative route, pointing to references/enterprise_research_methodology.md for detail.

State the source accessibility classification once (or defer to references/source_accessibility_policy.md) instead of repeating the rules in P0, P3, and the information-black-box section.

Move the illustrative Counter-Review Team SendMessage dispatch block into references/counter_review_team_guide.md, keeping only the manual default procedure inline.

DimensionReasoningScore

Conciseness

Mostly efficient — tables carry dense policy and there is no explanation of concepts Claude already knows — but significant duplication could be tightened: the Enterprise pipeline appears twice (the "Enterprise Workflow Overview" checklist and again as the "Specialized Pipeline" E1-E7 section, with E3/E4/E5 rules restated in an "E3-E7" recap), and source-governance rules recur across P0, P3, and the black-box section. More than minor trimming is needed, so it sits below the "efficient" anchor.

3 / 5

Actionability

Concrete and executable in most places: exact task-assignment field lists, per-phase status report strings, citation-registry and black-box output templates, the provider_runs.py plan command, and per-phase load directives. Minor gaps remain — the "SendMessage to: claim-validator" block is illustrative rather than runnable, and a few directives ("Create tasks only where separate evidence routes or expertise make the work clearer") are abstract.

4 / 5

Workflow Clarity

Clear P0-P7 sequence with explicit validation checkpoints — mandatory P6 counter-review, P7 cross-checks, L1/L2/L3 quality gates, per-phase status reports — plus degradation paths (sequential mode without subagents, narrow-or-stop when a channel is missing). The duplicated, interleaved dual Enterprise/General pipelines make the overall control flow harder to follow, keeping it below the top anchor.

4 / 5

Progressive Disclosure

All 16 referenced files exist and references are one level deep (verified), organized in a "Reference Files" table with a "When to Load" column and load-time directives ("load parallel-provider-ops.md before fan-out"). SKILL.md still inlines substantial material that belongs in references — source accessibility governance, black-box handling, and the duplicated enterprise pipeline — leaving minor organization gaps.

4 / 5

Total

15

/

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: explicit what and when clauses, bilingual natural trigger phrases, and explicit routing to sibling skills. Its main weaknesses are jargon in the trigger list (multi-route provider phrasing, product names like UniFuncs) and a fairly broad "write a report" trigger that could collide with general report-generation skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete deliverables ("evidence-tracked research reports", "parallel AI-provider/mode studies", "source-level synthesis"), but these read as product categories rather than a comprehensive list of concrete operations. Fits the anchor for several specific actions with minor gaps; short of the comprehensive multi-action anchor.

4 / 5

Completeness

Explicitly answers both what ("Creates evidence-tracked research reports and parallel AI-provider/mode studies...") and when ("Use for write a report, research reports, literature reviews...") with concrete trigger phrases, plus boundary routing. Matches the top anchor; the when-clause is fully explicit, not merely implied.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "write a report, research reports, literature reviews, market/industry analysis, competitive landscapes" plus bilingual triggers ("帮我调研一下 / 深度研究 / 综述报告"). "multi-route ChatGPT/Kimi/UniFuncs research" is jargon a user would not naturally say, keeping it below the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

Distinct research-report niche with explicit disambiguation ("For choosing technology use tech-selection; for competitor code analysis use competitors-analysis"). "write a report" is a moderately broad trigger that could overlap with report-formatting skills, so minor overlap risk remains rather than minimal.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (554 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
daymade/claude-code-skills
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.