CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-ticketing

Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.

Quality

72%

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 ./.agents/skills/memory-ticketing/SKILL.md
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.

An extremely lean, well-structured body with a clear sequenced flow and an excellent safety exclusion list, but it reads more like a system overview than an instruction set — it never tells Claude concretely how to emit an event or what a ticket looks like. Adding a minimal example of the JSONL ticket format would close the main gap without hurting conciseness.

Suggestions

Add a one-line example of a memory ticket (a single JSONL record) so the .agentlas/memory-tickets.jsonl format is executable knowledge rather than assumed.

Specify how a worker emits a `## Memory Event` (where in output, what fields it carries), since step 1 of the Flow is the skill's main actor-facing action.

Add one line describing what happens on Curator or Policy Gate rejection (retry, drop, or flag) to close the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The body is 25 lines with zero padding — every line ('Workers emit `## Memory Events`', the file list, the Never Store exclusions) carries information Claude could not infer, assuming full competence. It matches the 'lean and efficient; every token earns its place' anchor exactly.

5 / 5

Actionability

Concrete elements exist (exact paths like '.agentlas/memory-tickets.jsonl' and a specific exclusion list), but key executable details are missing: the ticket JSONL format, where and how a worker emits a `## Memory Event`, and what routing to which vault actually looks like. This matches 'some concrete guidance but incomplete; missing key details' rather than 4, whose guidance is mostly executable.

3 / 5

Workflow Clarity

The Flow section gives a clear five-step sequence with validation explicitly present as step 3 ('Memory Curator validates, redacts, deduplicates'), so checkpoints are named even if delegated. It is not 5 because there is no feedback loop (what happens when the Curator or Policy Gate rejects a ticket) — a minor validation gap consistent with the anchor 4.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed, and the three well-labeled sections (Required Files, Flow, Never Store) organize it cleanly. Per the rubric's simple-skill guidance, this earns a 5; nothing is inlined that belongs in a separate file, and no bundle files exist.

5 / 5

Total

17

/

20

Passed

Description

51%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 highly distinctive, niche trigger description with good exact-term keywords, but it is one-sided: it tells Claude when to activate while saying nothing about what the skill does. Adding a brief capability statement would lift both completeness and specificity.

Suggestions

Prepend a short 'what' clause before the 'Use when' trigger, e.g. 'Create and route memory tickets across the agentlas memory system. Use when adding...'.

State the concrete actions the skill performs (creating memory-map.json entries, wrapping Memory Events into tickets, routing rules) so specificity is not limited to file names.

Add a few natural-language synonyms or phrasings (e.g., 'memory ticketing', 'agent memory files') alongside the canonical proper nouns to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names concrete domain artifacts ("memory-map.json, vault-references.json, PM Soul memory ownership, Memory Curator routing") but never states any action the skill performs — it is a pure trigger list with zero capability verbs, matching the 'names the domain but actions are minimal or generic' anchor. It is not a 3 because no concrete action (not even 1-2) is described anywhere.

2 / 5

Completeness

Only 'when' is present ("Use when adding Memory Events, Memory Tickets...") with no 'what' clause describing what the skill actually does, which matches the anchor 'only when is present without what'. Although the 'when' is detailed and explicit, the complete absence of a 'what' keeps it at 2 rather than 3.

2 / 5

Trigger Term Quality

Good keyword coverage with exact file names including extensions ("memory-map.json", "vault-references.json") and role names ("PM Soul", "Memory Curator") that a user of this system would naturally say. It falls short of 5 because there are no synonyms or phrasings beyond the canonical proper nouns (e.g., 'memory ticketing', 'agent memory').

4 / 5

Distinctiveness Conflict Risk

Highly niche proper nouns and exact file paths ("PM Soul", "Memory Curator", ".agentlas" artifacts) create a clear trigger niche with minimal overlap with any other skill. Nothing generic remains that would fire the description for an unrelated request.

5 / 5

Total

13

/

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

agentlas-ai/Agentlas-OS

Path

.agents/skills/memory-ticketing/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.