BC Harvest
Mines one piece of content for LifeOS and/or ingests it into Cortex. USE WHEN harvest, harvest this, /harvest, /ha, mine this for the system, anything useful in this for us, what can LifeOS take from this, should we adopt anything from this, ingest to knowledge, save to knowledge, drop into knowledge, route to knowledge, add to the knowledge archive, archive this signal, capture this to knowledge, classify and route to knowledge. NOT FOR Cortex note ops, Upgrade / lu scans, Cortex recall, X PullBookmarks sweeps.
This skill mines content into LifeOS and routes it to Cortex: parses material, classifies, sends to knowledge storage. Triggers on commands like 'harvest this', 'mine for the system', 'ingest to knowledge'. Seven modules and one script in the bundle, but process score dropped to 58—logic works rough or instructions are incomplete. Quality at 82, safety at 99, so data doesn't leak everywhere. One medium-severity finding, no critical ones.
In practice: deploys across most platforms (Claude, Cursor, DeepSeek, etc.). The real question is whether it consistently delivers content to the right place or loses chunks along the way. Low process score hints at the latter. Install if you're ready to debug—otherwise expect an archive with gaps.
Mines one piece of content for LifeOS and/or ingests it into Cortex.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-useSKILL.md:50Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition)- **Idempotency:** Workflows enforces `UNIQUE(source, external_id)` — re-harvesting the same URL returns `output.status: "duplicate"`. The executor sidecar at `MEMORY/STATE/harvest-executor-state.json
detector
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 32 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2731 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (8 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 517: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.