CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

competitive-intel-watch

Scheduled delta monitoring against a prior competitive snapshot. Use when tracking competitors on a cadence: material shifts only, cited evidence, battle-card update flags, runs unattended.

Quality

77%

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/competitive-intel-watch/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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-organized, largely actionable workflow skill with a strong output schema and examples, weakened by repeated restatement of the same discipline and by progressive-disclosure pointers to bundle files that do not exist in the skill bundle.

Suggestions

Consolidate the "empty changelog is valid / no regeneration theater" message into a single Key Concepts or Pitfalls entry instead of restating it across Purpose, Key Concepts, and Common Pitfalls.

Ship the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) or remove the links, so the progressive-disclosure pointers resolve to real content.

Add a brief example of the 3-bullet search plan format in the Application step so that step is executable without reading the sibling autonomous-investigation skill.

DimensionReasoningScore

Conciseness

The body is information-dense with no basic-concept padding, but the core discipline is stated three times ("empty changelog is valid" in Purpose, Key Concepts, and Common Pitfalls; "regeneration theater" in Purpose and Pitfalls) and carries rhetorical flourishes ("cries wolf", "theater") that could be trimmed without loss.

3 / 5

Actionability

A concrete 6-step Application flow, a copy-paste output schema with exact fields, a 4-option Final Step with explicit accepted tokens, and two worked examples cover the common cases; the gap is that the "3-bullet search plan" format is never shown and the Fact/Inference labeling mechanics are delegated to sibling skills.

4 / 5

Workflow Clarity

The numbered 6-step sequence has real checkpoints — a 2-question budget, a search-plan gate ("Continue unless revised"), materiality filtering with explicit empty-cycle handling, and a carry-forward watchlist plus an Assumptions-to-Validate checklist; no explicit error-recovery feedback loop keeps it off the top anchor.

4 / 5

Progressive Disclosure

Structure and signaling are good — a clear References section, labeled sibling-skill links, and one-level-deep pointers to template.md and examples/sample.md — but the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) are not present in the bundle, so the disclosure resolves to dead ends rather than real deeper material.

3 / 5

Total

14

/

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 tight, well-structured description that answers what and when with concrete, third-person trigger language and a distinctive delta-monitoring niche. Minor gains are available in enumerating actions and adding a few synonym triggers.

DimensionReasoningScore

Specificity

The description lists several concrete behaviors — "material shifts only, cited evidence, battle-card update flags, runs unattended" — anchored to a clear domain (delta monitoring against a prior snapshot); not a flat 5 because these are framed as attributes rather than an enumerated action list like the PDF exemplar.

4 / 5

Completeness

It explicitly answers both halves — what ("Scheduled delta monitoring against a prior competitive snapshot") and when ("Use when tracking competitors on a cadence…") — with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"Use when tracking competitors on a cadence" plus "competitive snapshot", "battle-card", and "runs unattended" are natural phrases a competitive-intel user would say; a few synonyms (e.g. "competitor watch", "market intelligence") are absent, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The delta-vs-state framing, battle-card update flags, and unattended-cadence trigger carve a clear niche distinct from the sibling snapshot skill; minor overlap risk remains with the broader market-intelligence skill family.

4 / 5

Total

17

/

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

relative_links

Relative link issues: 3 missing, 9 suspicious

Warning

Total

14

/

16

Passed

Repository

deanpeters/Product-Manager-Skills

Path

skills/competitive-intel-watch/SKILL.md

Reviewed

Table of Contents

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.