CtrlK
BlogDocsLog inGet started
Tessl Logo

find-key-internal-sources

Use when a seller needs to find the best internal experts, owners, approvers, documents, channels, source-of-truth materials, or escalation routes for a customer question, product topic, competitive objection, implementation issue, account task, or other sales-support need. Route questions such as 'who knows about this?', 'what should I read?', 'where is the source of truth?', and 'which internal channel or document should I use?' here.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured, actionable routing skill with a clean progressive-disclosure split and concrete output template. The main room for improvement is tightening minor redundancy and making the implicit validation/stopping checkpoints more explicit in the workflow steps.

Suggestions

De-duplicate the reference-loading guidance: state it once in the 'Reference Loading' section and reference it from step 3 rather than repeating the conditions.

Add an explicit validation checkpoint in step 5 (e.g., 'Before returning, confirm each route has an evidence link or is labeled Likely/Possible; record gaps in Coverage Gaps') to convert the implicit confidence check into a visible gate.

Tighten abstract workflow headers like 'Build useful search facets' and 'Render the routing map' by leading with the concrete action (e.g., 'Construct bounded search facets' / 'Emit the routing map') so the header itself is actionable.

DimensionReasoningScore

Conciseness

The body is dense and mostly operational, with justified domain-term definitions (DRI, SME, decision forum) and specific numeric parameters, but has minor redundancy (reference-loading guidance is restated in step 3) and could be trimmed slightly.

4 / 5

Actionability

It provides a copy-paste-ready output template and concrete parameters (cap boost at +0.25, last 90 days, at most three candidates), but several workflow headers use abstract framing verbs ("Build useful search facets", "Render the routing map") alongside the concrete sub-bullets.

4 / 5

Workflow Clarity

Five well-sequenced steps with bounded passes, stopping rules, and an ambiguity feedback loop (bounded pass → ask one question); the skill is read-only so the destructive-cap does not apply, but validation is implicit (confidence labels, Coverage Gaps) rather than explicit validate-then-proceed gates.

4 / 5

Progressive Disclosure

The body is a clear overview that delegates detail to two real, one-level-deep reference files, each signaled with explicit load conditions ("Use [references/search-patterns.md] when...", "Use [references/company-context.md] only after the generic pass"), and neither reference nests further.

5 / 5

Total

17

/

20

Passed

Description

95%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 strong, third-person description that concretely states what it does and when to use it, with explicit natural-language trigger phrases. The only minor gap is limited verb diversity, which keeps specificity just below the top anchor.

DimensionReasoningScore

Specificity

The description lists a comprehensive set of concrete object categories ("internal experts, owners, approvers, documents, channels, source-of-truth materials, or escalation routes") but relies on only two action verbs ("find", "route"), so it sits just below the multi-verb 5 anchor.

4 / 5

Completeness

It explicitly answers both "what" (find experts/owners/approvers/docs/channels/source-of-truth/escalation routes) and "when" ("Use when a seller needs to find... for a customer question, product topic..."), with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes explicit natural trigger phrases users would actually say ("who knows about this?", "what should I read?", "where is the source of truth?", "which internal channel or document should I use?") alongside comprehensive role/object keywords.

5 / 5

Distinctiveness Conflict Risk

It carves a clear sales-support internal-routing niche with distinctive triggers (source-of-truth, approvers, escalation routes), minimizing overlap with generic search or doc skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
XiaomiMiMo/MiMo-Code
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.