AC manus-api
Interact with the Manus AI agent platform via its REST API. Use this skill whenever the user mentions Manus, manus.ai, Manus API, Manus tasks, Manus projects, or wants to delegate work to the Manus AI agent — including creating tasks, uploading files, managing projects, polling task status, continuing multi-turn conversations, or setting up webhooks. Also trigger when the user says "send to Manus", "ask Manus to", "have Manus do", "manus agent", or references task IDs, session IDs, or Manus file uploads. This skill handles session/task-ID tracking to prevent accidental task duplication — a critical concern since every POST to /v1/tasks without a taskId creates a NEW task and consumes credits. Trigger this skill even for simple Manus questions like "what's the status of my Manus task" or "list my Manus sessions."
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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:34Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -H "API_KEY: $MANUS_API_KEY" https://api.manus.ai/v1/tasks
vendor-host
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 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
- 30Running it twice. 13 mutating operations with no state check
- 40Consistency. Frontmatter name (manus-api) differs from the folder (manus-skill)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 2213 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 823: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 19 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.