Install
$ agentstack add skill-zjp1997720-zhijian-skills-light-plan-and-work ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Light Plan and Work
Planning and doing are one continuous workflow.
Route before planning
Read the request, relevant project instructions, current files, and repository state. Choose one route:
- Direct execution: one or two obvious actions. State a one-line brief and do them; do not manufacture a plan.
- Light plan and work: the outcome is concrete, the scope is bounded, and 3–7 steps can complete and verify it.
- Specialist Skill: a narrower installed Skill owns the artifact or domain. Use it, with this Skill only as the execution wrapper when useful.
- Discovery or brainstorming: the user is still choosing the problem, audience, concept, story, or direction. Use a discovery Skill before planning.
- Heavy workflow: use the project's full specification or plan/work system when consequence, ambiguity, or coordination cost is high.
Heavy conditions include destructive or sensitive operations, migrations, public API changes, cross-system architecture, releases, multiple owners, unresolved acceptance criteria, and explicit requests for a full specification or Compound Engineering. Read [routing and verification](references/routing-and-verification.md) when the route is unclear.
Execute
- Lock a compact execution brief: Goal, Deliverable, Boundary, and Acceptance.
- Resolve reversible choices yourself. Ask one blocking question only when the answer changes the outcome or requires new authority.
- Use the host plan tracker for 3–7 observable steps, with at most one step in progress. Each step must produce or verify something.
- Start after the plan is visible. Read before editing, preserve unrelated work, follow project instructions, and keep the plan aligned with evidence.
- If a heavy condition appears, preserve completed safe work, pause the affected mutation, explain the evidence, and switch to the heavier workflow.
- Verify in proportion to risk; hand back the result, artifacts, evidence, and residual risk.
Do not create a durable plan file by default. Create one only for an explicit request, future resumption, external handoff, multiple owners, or a lasting design decision, and follow the project's existing plan location.
Maintain trigger boundaries with evals/trigger_cases.json and output behavior with the baseline comparisons in evals/output/cases.jsonl.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: zjp1997720
- Source: zjp1997720/zhijian-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.