Tessl • The management layer for AI agent skills

SkillPublic

reset-cursor-acp

Reset a stuck Cursor ACP thread in your chat app and reload its configuration. Use only when the user explicitly invokes /reset-cursor-acp.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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, well-structured operational runbook: an unambiguous reset procedure with explicit verification and a symptom-cause-fix table, plus a valuable Do-not section guarding against dangerous generic actions. The only weakness is placeholder indirection (`<reset-script>`, `<app-cli>`, vague thread-list command) that forces the reader to resolve concrete commands.

Dimension	Reasoning	Score
Conciseness	Every line carries app-specific knowledge Claude cannot infer — the per-thread subprocess model, "There is no global Cursor ACP server", the "Failed to initialize session services" login symptom, the session/load failure mode — with no padding or generic explanation. This matches anchor 5 (lean and efficient; every token earns its place), not anchor 4, because there is no over-explanation to trim.	5 / 5
Actionability	The reset section gives a concrete, flag-documented command block (`<reset-script> <thread-id>`, `--self`, `--dry-run`, `--kill-all`) that maps to the real scripts/reset-cursor-acp.sh, and known causes pair symptoms with fixes. It stops short of anchor 5 because the placeholders `<reset-script>` and `<app-cli>` must be resolved by the reader and thread-ID discovery is only "the app's status or thread-list command" rather than a concrete command.	4 / 5
Workflow Clarity	The sequence is explicit — run the script, then a dedicated Verify section ("Send one short message to verify a fresh agent responds"), then diagnose via Known causes before another reset — with feedback loops (symptom → fix → "then reset") and a `--dry-run` guard for the destructive kill. This matches anchor 5 (explicit validation steps and error-recovery loops), and the destructive-operation cap of 3 does not apply since validation is present.	5 / 5
Progressive Disclosure	The ~49-line body is cleanly sectioned (How resets work, Quick reset, Verify, Known causes, Do not) with a single real bundle file (scripts/reset-cursor-acp.sh), and details like CLI internals correctly live in the script rather than the body. It falls short of anchor 5 because the script is referenced through the `<reset-script>` placeholder with "Resolve <reset-script> relative to this SKILL.md" instead of a clear, well-signaled path such as scripts/reset-cursor-acp.sh.	4 / 5
	Total	18 / 20 Passed

Description

82%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 lean, well-formed description for a narrowly scoped utility: concrete what, an explicit slash-command trigger consistent with its disable-model-invocation frontmatter, and near-zero conflict risk. The main gap is capability coverage — the script also handles orphan cleanup and CLI health checks that the description never mentions.

Suggestions

Add one or two more concrete capabilities to the description, e.g. mention that it also cleans up orphaned cursor-agent processes and checks CLI version/login status, so specificity reaches the 'several specific actions' level.

Add one or two natural trigger synonyms (e.g. 'hangs' or 'frozen Cursor agent') so users phrasing the problem differently still map to this skill, even though invocation is slash-command-only.

Dimension	Reasoning	Score
Specificity	"Reset a stuck Cursor ACP thread in your chat app and reload its configuration" names the domain plus two concrete actions, but capabilities like orphan cleanup, login/version health checks, and per-thread targeting are not stated. It matches anchor 3 (1-2 concrete actions, not comprehensive) rather than anchor 4, which requires several specific actions with only minor gaps.	3 / 5
Completeness	It clearly answers both parts: the what ("Reset a stuck Cursor ACP thread in your chat app and reload its configuration") and an explicit, concrete when ("Use only when the user explicitly invokes /reset-cursor-acp"). The trigger guidance is fully explicit with a concrete invocation phrase, matching anchor 5 rather than anchor 4's softer 'could be more specific' case.	5 / 5
Trigger Term Quality	Natural terms a user would say are present — "Cursor", "ACP", "stuck", "thread", "reset", plus the explicit "/reset-cursor-acp" invocation — giving good keyword coverage. It falls short of anchor 5 because common synonyms like "hangs", "frozen", "unresponsive", or "Cursor agent" are missing.	4 / 5
Distinctiveness Conflict Risk	"Reset a stuck Cursor ACP thread" carves out a clear niche with distinct trigger terms (Cursor, ACP, stuck thread, /reset-cursor-acp) that virtually no other skill would claim. Minimal conflict risk, matching anchor 5.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: davidondrej/skills
Path: skills/agent-orchestration/reset-cursor-acp/SKILL.md
Revision: 0a86632

Reviewed: 20 days ago

Discovery Implementation Validation

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.

reset-cursor-acp

Table of Contents

Is this your skill?