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

62%

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 ./skills/intelligence-collection-disciplines/SKILL.md

Quality

Content

53%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 rich, actionable reference skill with strong source coverage and a clear fusion workflow. Its main weaknesses are missing bundle files referenced in the body and the absence of explicit verification checkpoints before acting on conclusions.

Suggestions

Create the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) under references/ or assets/, or remove/rewrite the links — broken references sink progressive disclosure.

Add an explicit verification checkpoint to the fusion step (e.g. "Before escalating to actionable, confirm signals come from ≥3 independent disciplines and label each Fact/Inference/Assumption") to lift workflow clarity above 3.

Trim rhetorical flourishes and taglines to tighten the body toward the lean anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens (source tables, signal→inference chains, fusion cadence), but at ~380 lines with some rhetorical flourish ("Stop doing competitive research like a term paper," "The Wiretap You're Allowed to Have") it could be tightened; mostly efficient but with padding.	3 / 5
Actionability	Provides concrete, named sources (SEC EDGAR, Eurostat, patents.google.com, crt.sh), specific signal→inference chains, and an executable TAM/SAM/SOM recipe — mostly actionable guidance with minor gaps (no literal copy-paste commands, but justified for a reference skill).	4 / 5
Workflow Clarity	Sequencing is present (per-discipline workflow, fusion cadence table, confidence-stacking rule) but there are no explicit validate/verify checkpoints before acting on fused conclusions; for research that can drive roadmap bets this sits at the "sequence present, checkpoints implicit" anchor.	3 / 5
Progressive Disclosure	Sections are well organized and the body references [`template.md`](template.md), [`examples/sample.md`](examples/sample.md), and [`examples/sample-industrial.md`](examples/sample-industrial.md) — but none of these bundle files exist in references/, scripts/, or assets/, so the navigation signals are broken and the promised detail is absent.	2 / 5
	Total	12 / 20 Passed

Description

71%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 distinctive, capability-rich description with an explicit use-when clause. Its main weakness is an abstract trigger phrase rather than the natural language users would actually say.

Suggestions

Replace the abstract trigger "Use when one-source research isn't enough" with concrete user phrasing, e.g. "Use when validating a suspected competitor move, sizing a market with defensible data, or cross-checking signals across independent sources."

Name the disciplines inline (e.g. "eight disciplines — OSINT, FININT, GEOINT, TECHINT, HUMINT, SIGINT, MASINT, fusion") to lift specificity from 4 to 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — "eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion" — with only minor gaps in coverage, fitting the "several specific actions" anchor; not a 5 because it stops short of naming the full set of disciplines.	4 / 5
Completeness	Clearly answers "what" (the disciplines, chains, fusion) and provides an explicit "Use when..." clause, but the "when" is somewhat generic ("one-source research isn't enough") rather than concrete trigger phrases, placing it between the 3 and 5 anchors.	4 / 5
Trigger Term Quality	Contains relevant keywords ("competitive research," "collection disciplines," "OSINT," "MASINT," "fusion") but the trigger clause "Use when one-source research isn't enough" is abstract framing rather than the natural phrases a user would say, missing common variations; sits above 2 and below 4.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (intelligence-agency collection disciplines for competitive research) with distinct triggers and minimal overlap risk with general research skills.	5 / 5
	Total	16 / 20 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: 1b5a524

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.