CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

accint-solve

Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/accint-solve/SKILL.md

The canonical home for this skill is accint-solve in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, lean routing skill whose main solve/continue loop is concretely specified with exact MCP call syntax, explicit branching, and a built-in calibration convention. The only real gaps are the unspecified arguments of the outcome call and the implicit iteration/timing behavior around it.

Suggestions

Show the argument shape for the outcome call as concretely as the solve/continue calls, e.g. `acc_act(runtime="outcome", input={"commitment_id": ..., ...})` instead of a bare ellipsis.

State explicitly that if `acc_act(runtime="continue")` returns another brain_frame, step 3 repeats until a final result arrives.

Fix the grammar in the When to Use line: 'when you need route a goal' should read 'when you need to route a goal'.

DimensionReasoningScore

Conciseness

Roughly 20 lean lines with zero filler and no explanation of concepts Claude already knows; every line is operational ('Routing sugar over the two MCP verbs — no logic lives here'). Assumes competence throughout, so every token earns its place.

5 / 5

Actionability

Concrete near-copy-paste calls are given for solve and continue, including the exact format 'PREDICT: <0.00-1.00> <why>'. Not 5 because step 6's `acc_act(runtime="outcome", ...)` leaves its arguments unspecified; not 3 because the main loop calls are fully specified with parameter shapes.

4 / 5

Workflow Clarity

Clear numbered sequence with explicit branching on final vs brain_frame and the invariant 'Never leave a received frame unresolved; never solo-derive outside the loop'. Not 5 because the loop-back behavior when continue returns another frame and the timing of the outcome step ('later') are implicit; not 3 because branching and invariants act as explicit checkpoints.

4 / 5

Progressive Disclosure

An under-50-line single-purpose skill with no bundle files and no content that belongs in external references; the 'When to Use' section plus a numbered procedure is well-organized, which scores 5 under the simple-skill note.

5 / 5

Total

18

/

20

Passed

Description

55%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.

The description states the 'what' concretely with exact API calls and is highly distinctive within its niche, but it omits any 'when to use' trigger guidance and leans on plugin jargon rather than natural user phrasing. These two weaknesses hold it to a middling score despite strong specificity and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to solve, pursue, or deliberate on a goal through acc, or when an acc brain_frame needs a proposal.'

Include one or two natural synonyms users would actually say (e.g. 'run a goal through acc', 'solve with acc') alongside the API jargon.

Mention the outcome/commitment-close step so the description covers the skill's full scope.

DimensionReasoningScore

Specificity

Names three concrete actions with exact API surface ('Route a goal through acc's scored-memory loop via acc_act(runtime="solve")', 'deliberate any returned brain_frame', 'submit via continue'), with a minor coverage gap — the outcome/commitment-close step from the body is omitted. Not 5 because coverage is incomplete; not 3 because it goes beyond 1-2 actions with function-call-level specificity.

4 / 5

Completeness

The 'what' is clear (route a goal via the solve runtime, deliberate returned frames, submit via continue), but there is no 'Use when...' clause or equivalent trigger guidance — the 'when' is entirely absent, capping this dimension at 3. Not 4 because the 'when' is not weakly present, it is missing altogether.

3 / 5

Trigger Term Quality

The description is dominated by plugin jargon ('scored-memory loop', 'brain_frame', 'acc_act'); only 'goal' and 'solve' resemble natural user phrasing, and common variations users would actually say (e.g. 'solve this with acc', 'run a goal through acc') are missing. Not 1 because 'acc', 'goal', and 'solve' are relevant keywords for users of this system; not 3 because natural-phrase coverage is thin.

2 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — acc runtime routing — with highly distinctive tokens (runtime="solve", brain_frame, continue) that no generic skill would match, and it explicitly separates the solve and continue runtimes, minimizing overlap even with sibling acc skills.

5 / 5

Total

14

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/accint-solve/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.