CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frame-problem

Sense-making before action. Classify problem using Cynefin triangulation (3 tests + decomposition) to route to the right skill chain. Use when: frame, what approach, how should I start, which skill, where to begin, unsure what to do. NOT for known tasks — just do them.

Quality

89%

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

92%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 engineered routing skill: complete decision table, literal templates, and a validated multi-step workflow with user confirmation gates. Its only real weakness is minor redundancy between the anti-patterns and the procedure text.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence (Cynefin domains are used without lecturing), with no padded background. Minor redundancy keeps it below the 5 anchor: the T1-override rule appears both in Step 1 ("Do not let T1 win alone against T2 and T3") and again as a full anti-pattern section with a near-duplicate example block, and the seven NEVER entries each carry a Why that could sometimes be trimmed.

4 / 5

Actionability

Fully concrete instruction-level guidance: literal copy-paste templates (the "🎯 Auto-classified" proposal, the domain map, the blank-AskUserQuestion fallback notice), a complete routing table mapping every domain to verb/skill/OpenSpec, and exact question-answer handling rules. For an instruction-only skill this is the 5 anchor: specific guidance covering the common cases.

5 / 5

Workflow Clarity

The sequence (Step 0 auto-classify → 1 triangulate → 1.5 decompose → 2 classify/route → 3 handoff) is explicit with validation checkpoints throughout: an 80% confidence threshold, the Adjacent Domain Challenge, a blank-answer guard, and user confirmation gates ("Adjust / Confirm / Re-frame", "Start chain / Re-frame / Skip framing") with re-frame feedback loops on disagreement. Matches the 5 anchor's explicit-validation and error-recovery criteria.

5 / 5

Progressive Disclosure

The body is a well-signaled overview with 8 one-level-deep references, all verified to exist with real content, each referenced at the point of need ("Load references/triangulation-tests.md for the exact wording") and catalogued with purpose in the References section. No nesting, no orphan links — matches the 5 anchor.

5 / 5

Total

19

/

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 strong description: concrete capability statement, explicit trigger phrase list in natural user language, and a clear negative boundary. The main gap is slight compression of the capability surface into one clause and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

"Classify problem using Cynefin triangulation (3 tests + decomposition) to route to the right skill chain" lists several specific actions (triangulate via 3 tests, decompose, route) with the mechanism stated. Minor gaps in coverage keep it below the comprehensive 5 anchor; it is clearly above the 1-2-action level of anchor 3.

4 / 5

Completeness

It clearly answers both what ("Classify problem using Cynefin triangulation ... to route to the right skill chain") and when ("Use when: frame, ... unsure what to do"), plus an explicit negative boundary ("NOT for known tasks — just do them"). This matches the 5 anchor: explicit what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use when: frame, what approach, how should I start, which skill, where to begin, unsure what to do" gives good natural-phrase coverage that users would actually say. A few natural variants (e.g. "stuck", "can't decide") are missing, so it does not reach the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The Cynefin triangulation framing is a distinct niche with specific triggers, and "NOT for known tasks" sharpens the boundary. "Which skill" and "where to begin" carry minor overlap risk with generic planning/orchestration skills, matching anchor 4 rather than the minimal-conflict 5.

4 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

pantheon-org/tekhne

Path

skills/software-engineering/frame-problem/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.