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

71%

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 ./plugins/agentic-awesome-skills-claude/skills/accint-solve/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body delivers a clear, actionable routing procedure with strong error-handling boundaries, appropriate for a thin MCP-verb wrapper. Its weaknesses are redundancy — the When to Use and Example sections restate the description — and elided parameters that keep the guidance just short of fully executable.

Suggestions

Delete or replace the Example section (it only re-quotes the description) with a real worked example showing an acc_act solve call, a sample brain_frame response, and the matching continue submission.

Remove the verbatim description duplication in When to Use and keep only the branch-specific guidance that is new information.

Specify the acc_act(runtime="outcome", ...) parameters and what a valid proposal_text looks like so all three verbs have complete invocation shapes.

DimensionReasoningScore

Conciseness

The steps and Execution boundaries are lean, but the When to Use section repeats the frontmatter description verbatim ("Use this skill when you need route a goal through acc's scored-memory loop..."), and the Example section merely re-quotes that description as a fake user request, adding no value.

3 / 5

Actionability

Gives concrete calls — `acc_act(runtime="solve", input="<the goal>")`, `acc_act(runtime="continue", input={"frame_id": ..., "submit_token": ..., "proposal_text": ...})` — plus the exact `PREDICT: <0.00-1.00> <why>` format, but ellipsis placeholders and the unspecified `acc_act(runtime="outcome", ...)` parameters leave minor gaps versus copy-paste-ready guidance.

4 / 5

Workflow Clarity

A clear 6-step sequence with branch handling (final vs brain_frame), explicit stop conditions ("Stop when the user cancels, the tool fails, or a frame needs unavailable input") and retry-safety rules ("A retry is safe only when the actual integration confirms its idempotency contract"), but the outcome-closure step and malformed-frame handling are underspecified.

4 / 5

Progressive Disclosure

A short (~45-line) skill with no bundle files and well-organized sections (When to Use, steps, Example, Limitations, Execution boundaries); the vacuous Example section and undocumented concepts like 'commitment id' and 'Work Model' leave minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

62%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 concrete, distinctive description that names exact verbs and actions, but it doubles as mechanism documentation rather than user-facing trigger text. It lacks any 'Use when...' guidance and leans on system jargon over natural phrasing.

Suggestions

Add an explicit trigger clause (e.g., 'Use when the user asks to run a goal or task through acc's scored-memory loop, or mentions acc, solve, or brain frames') to raise completeness and trigger-term quality.

Include natural synonyms such as 'task', 'problem', or 'reason through' alongside the jargon so users' phrasings match without knowing internal terms.

Briefly state the purpose/outcome of the loop (e.g., what closing a commitment achieves) so the description covers the full capability, not just the first two verbs.

DimensionReasoningScore

Specificity

Lists several concrete actions with the exact invocation — "route a goal through acc's scored-memory loop via acc_act(runtime=\"solve\")", "deliberate any returned brain_frame", "submit via continue" — but omits the outcome/closure stage and frame-type coverage, so it is not the comprehensive level 5.

4 / 5

Completeness

The "what" is clearly stated (route via acc_act runtime="solve", deliberate frames, submit via continue) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

Contains some relevant keywords ("goal", "solve", "submit", "continue") but is dominated by system jargon ("scored-memory loop", "brain_frame", "acc_act") and misses natural variations or synonyms like "task", "reason", or "problem" that a user would actually say.

3 / 5

Distinctiveness Conflict Risk

Highly distinctive vocabulary — "acc's scored-memory loop", "brain_frame", "acc_act" — carves out a clear niche tied to one specific tool with minimal risk of triggering for the wrong skill.

5 / 5

Total

15

/

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

sickn33/agentic-awesome-skills

Path

plugins/agentic-awesome-skills-claude/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.