CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deep-research

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

Quality

69%

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

Quality

Content

71%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.

The body is a highly actionable, well-organized CLI usage guide with concrete commands, clear workflow sequencing, and explicit exit codes. Its main weaknesses are redundant use-case sections and references to bundle files that are not present to verify.

Suggestions

Merge the duplicated 'When to Use This Skill' and 'Best Use Cases' sections into one, and drop the verbatim repeat of the description in the intro.

Add brief error-recovery guidance for exit code 1 (e.g. retry after timeout, check GEMINI_API_KEY) to close the feedback-loop gap.

Either ship the referenced scripts/research.py and requirements.txt in the bundle or move inlined reference material (cost/token table, use-case detail) into a references file with clear links.

DimensionReasoningScore

Conciseness

"When to Use This Skill" and "Best Use Cases" duplicate nearly the same list (market analysis, competitive landscaping, literature reviews, due diligence), and the opening line repeats the frontmatter description verbatim. Mostly efficient but with clear tightening opportunities; not 4 because whole-section duplication exceeds minor trimming, not 2 because there is no padding explaining concepts Claude already knows.

3 / 5

Actionability

Every section gives copy-paste-ready commands with concrete flags (--query, --format, --stream, --no-wait, --status, --wait, --continue, --list) plus exact exit codes, covering the common cases. Fully executable guidance matching anchor 5.

5 / 5

Workflow Clarity

The Workflow section lays out a clear 5-step sequence with monitoring checkpoints (--stream / --status) and wait behavior, and Exit Codes document outcomes. Not 5 because there is no error-recovery guidance for exit code 1 (API error, timeout) — no fix-and-retry loop; not 3 because sequence and checkpoints are explicit and the skill is non-destructive.

4 / 5

Progressive Disclosure

The single file is well-sectioned, but it references scripts/research.py and requirements.txt that are not present in the bundle (no references/, scripts/, or assets/ directories exist), and inline detail like the cost/token table could live in a reference file. Fits anchor 3 (structure present but references problematic); not 4 because unverifiable/missing referenced files are more than a minor organization gap.

3 / 5

Total

15

/

20

Passed

Description

55%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.

The description gives a clear, moderately specific statement of what the skill does, but omits any "when to use" trigger guidance and relies on a thin set of keywords. Adding an explicit "Use when..." clause with concrete natural-language triggers would address both weaknesses.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. "Use when the user asks for deep research, literature reviews, market analysis, competitive landscaping, or due diligence."

Include natural keyword variations and synonyms in the description (deep research, literature review, due diligence, cited sources) rather than only in the body.

Distinguish the skill from generic search/report-writing by naming its hallmark traits (multi-minute autonomous, multi-step research with citations) in the description.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("plan, search, read, and synthesize information into comprehensive reports") but leaves minor coverage gaps such as citations, follow-up questions, and output formats. It fits anchor 4 (several specific actions with minor gaps) better than 5 (not comprehensive) or 3 (well beyond 1-2 actions).

4 / 5

Completeness

It clearly answers "what" (autonomous research that plans, searches, reads, synthesizes into reports) but has no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because "when" is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

"research" and "reports" are natural user terms, but the description misses common variations and synonyms a user would actually say — "deep research", "literature review", "due diligence", "market analysis" (the latter appear only in the body, not the description). Fits anchor 3: some relevant keywords, missing variations.

3 / 5

Distinctiveness Conflict Risk

"Run autonomous research tasks" narrows the niche somewhat, but the generic "research"/"reports" vocabulary overlaps with general web-search, report-writing, and summarization skills. Fits anchor 3 (somewhat specific but overlap risk remains); not 4 since no distinctive trigger phrases carve out the niche.

3 / 5

Total

13

/

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

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 8 missing

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/deep-research/SKILL.md

Revision

64adc55

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill