deep-research

Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.

Quality

96%

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

Quality

Content

92%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 highly actionable with executable commands and a clear, validated multi-stage workflow, and it practices good progressive disclosure via verified one-level references. It is slightly verbose in the boundary/differentiation prose but otherwise strong.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows, but the 'Decide if this is the right tool' table, 'Boundaries', and 'Differentiation from summarize' sections add modest padding that could be trimmed slightly. It is noticeably above the midpoint anchor but not fully lean.	4 / 5
Actionability	Each of the three stages is given as a copy-paste-ready command with concrete flags (--depth, --round, --print-fetches, --record) and a complete JSON evidence schema, covering the common execution cases.	5 / 5
Workflow Clarity	A clear Scope→Plan→Iterate (×N)→Compile→Deliver sequence is stated up front, with the plan's `done` flag acting as an explicit validation/termination checkpoint and the 'compile never invents sources' invariant providing a feedback guard.	5 / 5
Progressive Disclosure	The body is a concise overview with well-signaled one-level-deep references to references/methodology.md and references/sources.md (both verified to exist), and scripts are kept in a separate scripts/ directory rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

100%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 is specific, complete, and clearly differentiated, using third-person voice throughout and providing natural trigger terms with explicit 'when' guidance. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'explicit methodology, evidence tracking, and citation-tagged synthesis', 'maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations' — giving comprehensive, non-abstract coverage.	5 / 5
Completeness	Explicitly answers both 'what' (multi-round research with methodology, evidence tracking, citation-tagged synthesis across three stages) and 'when' (the 'Trigger on…' clause), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides natural trigger phrases users would actually say ('deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation') with synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Explicitly distinguished from the `summarize` skill and states the two 'share no trigger words by design', giving a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/deep-research/SKILL.md
Commit: 94ac35e

Reviewed: 4 days 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.