intelligence-collection-disciplines

Run competitive research like an intelligence agency: eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion. Use when one-source research isn't enough.

Quality

81%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A rich, highly actionable tradecraft playbook with a clear fused workflow and explicit validation gates. Its weak spots are stylistic verbosity that could be trimmed and progressive-disclosure references that point to bundle files which do not exist.

Suggestions

Trim the editorial taglines under each discipline (e.g. "The Journalist's Desk", "Follow the money...") to one functional line to cut length without losing the source tables and inference chains.

Create the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) so the in-body links resolve, or remove the links and inline only what is needed.

Move the eight per-discipline free/paid source tables into a single references file linked from a concise overview, keeping SKILL.md focused on the workflow, fusion rule, and discipline-selection logic.

Dimension	Reasoning	Score
Conciseness	Content is dense and assumes Claude's competence (no basic-concept explanations), but the ~380-line body carries stylistic prose such as "Stop doing competitive research like a term paper" and "Companies lie in press releases. They lie less in filings, because lying there is a felony" that could be trimmed, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Highly concrete instruction guidance: named sources ("SEC EDGAR", "patents.google.com", "crt.sh", "ImportYeti"), explicit signal→inference chains, a fillable fusion table, and a TAM/SAM/SOM recipe with formulas — copy-paste ready tradecraft as the top anchor requires for an instruction skill.	3 / 3
Workflow Clarity	Clear sequenced workflow (instantiate → select disciplines → collect → fuse → verdict) with explicit checkpoints: "If [DECISION] is blank, stop" and the confidence-stacking thresholds "1 discipline = watch item; 2 = working hypothesis; 3+ = actionable intelligence", plus an error-recovery direction ("conflicting disciplines = someone is bluffing — dig").	3 / 3
Progressive Disclosure	Sections and references are clearly signaled (e.g. "[`template.md`](template.md)", "[`examples/sample.md`](examples/sample.md)"), but those referenced bundle files are absent from the bundle and the full per-discipline source tables are inline rather than split out, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 well-crafted description that states concrete capabilities, an explicit use-trigger, and a distinctive niche. Its only weakness is heavy reliance on intel-community jargon over the everyday terms a PM would naturally say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion" — matching the anchor that names several specific actions rather than vague language.	3 / 3
Completeness	Answers both what ("Run competitive research like an intelligence agency: eight collection disciplines..., signal-to-inference chains, and fusion") and when ("Use when one-source research isn't enough."), with an explicit 'Use when' clause as the top anchor requires.	3 / 3
Trigger Term Quality	"competitive research" and the trigger "Use when one-source research isn't enough" are natural, but the rest leans on intel jargon (OSINT/MASINT, signal-to-inference, fusion); common user variations like "competitor analysis" or "market intelligence" are missing, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The intelligence-collection-disciplines framing for competitive research is a clear, narrow niche with a distinct trigger unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing, 4 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/intelligence-collection-disciplines/SKILL.md
Commit: 9971018

Reviewed: 3 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.