CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oma-market

Research customer pain points, trends, and competitors through the OMA market engine. Use for market discovery or voice-of-customer analysis.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-market/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 tightly written orchestration skill: precise commands, explicit failure and recovery handling, and a validated output loop. The main weaknesses are a partially incomplete code example, some repeated statements, and a References section whose target files are absent from the bundle.

Suggestions

Ship the referenced bundle files (resources/intent-rules.md, resources/output-laws.md, resources/frameworks/, resources/checklist.md, resources/error-playbook.md, resources/execution-protocol.md) — none are present, so every reference in the References and Dependencies sections currently dangles.

State the brief output path (`.agents/results/market/{topic-slug}-{YYYYMMDD}.md`) once and the detect-trap exit-2 refusal rule once, instead of repeating each across Goal/Expected outputs/Resource scope/Exit and Failure-and-recovery/Step 1.

Make the bash example self-contained: show how `$QUERY_PLAN_FILE` is produced (or inline a minimal plan) so the canonical command path is copy-paste runnable end to end.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows, but it repeats the brief output path in four places (Goal, Expected outputs, Resource scope, Exit) and restates detect-trap exit-2 handling in both "Failure and recovery" and Step 1 — minor trimming opportunities that keep it below a 5.

4 / 5

Actionability

Concrete executable commands with exact flags, exit codes, and paths (`oma market detect-trap "<topic>"`, `oma market resolve --json`, `oma market run ... --emit=compact`), plus a 5-minute timeout. The bash example is not fully copy-paste ready (an ellipsis stands in for upstream Steps 0–0.75 and `$QUERY_PLAN_FILE` is never defined), and several steps defer to the upstream contract, so minor gaps remain.

4 / 5

Workflow Clarity

An 8-step canonical command path in explicit order, with a preflight gate (detect-trap), per-failure handling (exit 2/4, resolve not ok, non-zero engine exit), and a validation feedback loop in Step 8 ("run the self-check ... fix and re-check"), plus a referenced checklist — matching the level-5 anchor's explicit checkpoints and error-recovery loops.

5 / 5

Progressive Disclosure

The References section is well signaled and one level deep (execution-protocol, intent-rules, output-laws, selected framework, checklist, error-playbook), but none of the referenced `resources/` files — nor the `../_shared/runtime/route-selection.md` path — exist in the provided bundle, so the navigation structure cannot actually be followed; scored against the actual (empty) bundle structure, this is more than the minor gap of a 4.

3 / 5

Total

16

/

20

Passed

Description

70%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 solid description that states concrete capability areas and includes an explicit use-when clause with natural trigger terms. Its main limits are a single generic verb for the actions and a when-clause that covers only part of the stated capabilities.

DimensionReasoningScore

Specificity

"Research customer pain points, trends, and competitors through the OMA market engine" names the domain and three research targets, but relies on a single generic verb ("research") applied to different objects rather than several distinct concrete actions like the level-4 anchor's "extracts / fills / converts".

3 / 5

Completeness

Both parts are present: the "what" (research pain points, trends, competitors via the OMA market engine) and an explicit "Use for market discovery or voice-of-customer analysis" when-clause. The when-clause is narrower than the what (e.g., it omits trend and competitor triggers), keeping it below the level-5 anchor's fully concrete, matching trigger phrases.

4 / 5

Trigger Term Quality

Natural trigger phrases are present — "customer pain points", "trends", "competitors", "market discovery", "voice-of-customer" — which users would plausibly say. Common synonyms such as "market research", "competitive analysis", or "user complaints" are missing, so coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The "OMA market engine" pin and voice-of-customer framing give it a mostly distinct niche with minor overlap risk against generic research/search skills; broad phrases like "trends" could still collide with related research skills, so it is not at the minimal-conflict level of 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

first-fluke/oh-my-agent

Path

.agents/skills/oma-market/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.