deep-research

Multi-directional deep research with sub-agents, scoring, source verification and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces an executive summary plus a markdown report.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/flowai-engineering/skills/deep-research/SKILL.md

Quality

Content

70%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-sequenced, actionable multi-phase workflow with strong validation checkpoints and feedback loops. Its main weaknesses are verbosity in the search-method instruction examples and a broken/missing worker reference plus inlined detail that would benefit from being split into reference files.

Suggestions

Create the referenced `deep-research-worker.md` (or fix the path) so the line 102 reference resolves to a real bundle file.

Move the four per-method search-instruction blocks into a single `references/search-methods.md` and summarize the detection table inline, cutting roughly 40 lines from SKILL.md.

Extract the worker prompt template and the Phase 3 scoring rubric into `references/worker-spec.md`, keeping only the invocation summary in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and procedural, but the four full search-method instruction blocks (built-in, playwright-cli, playwright-mcp, other MCP) are repetitive and padded, and the ~230 lines could be tightened without losing clarity.	3 / 5
Actionability	Provides concrete executable guidance — `mktemp -d` command, exact playwright-cli shell commands, `browser_navigate` calls, and a complete worker prompt template with a scoring table — with only minor gaps around runtime-filled placeholders.	4 / 5
Workflow Clarity	The Phase 0→5 sequence is explicit with validation checkpoints throughout: the Phase 2 pass/fail check table, Phase 3 escalation threshold and retry loop, and the Phase 5 report-integrity checklist provide clear feedback loops for a batch operation.	5 / 5
Progressive Disclosure	Section structure is clear and `assets/report_template.md` is a real one-level reference, but the body inlines detail that belongs in separate files (the four search-method instruction blocks, the full worker prompt template, scoring rubrics), and the `deep-research-worker.md` reference at line 102 points to a file that does not exist in the bundle.	3 / 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, third-person description that states concrete capabilities and gives explicit trigger guidance for when to use the skill. It is slightly held back by broad trigger terms that could overlap with generic research skills.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions — "sub-agents", "scoring", "source verification", "cited synthesis", "executive summary plus a markdown report" — but the actions are listed as a run rather than fully enumerated, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both what ("Multi-directional deep research with sub-agents, scoring, source verification and cited synthesis") and when ("Use for comprehensive research, deep analysis, or evidence-backed answers") with concrete trigger phrases, matching the anchor-5 pattern.	5 / 5
Trigger Term Quality	"comprehensive research", "deep analysis", and "evidence-backed answers" are natural phrases a user would say, with good coverage of common variations, though a few synonyms (e.g., "literature review", "source review") are missing.	4 / 5
Distinctiveness Conflict Risk	The multi-directional + sub-agent + verification + cited-synthesis niche is distinct, but the "comprehensive research" / "deep analysis" triggers are broad enough to overlap with general research or analysis skills, leaving minor conflict risk.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai-engineering/skills/deep-research/SKILL.md
Commit: ad81ae6

Reviewed: 8 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.