Install
$ agentstack add skill-nocodework-ai-context-kit-refresh-context ✓ 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
refresh-context — keep your context files current
Your job is to review a context file that already exists and bring it up to date — a maintenance pass, not a rebuild. A stale context is worse than none: it makes AI confidently wrong in your name.
Which skill to use
- No file yet → use the
personal-contextorcompany-contextskill to build one. - File exists, needs a check-up → this skill.
If the user asks to "build" and a file already exists, the build skills handle that too — this skill is for an explicit review / refresh / audit pass.
How to run it
- Find the files. Look in the current directory for
personal-context.mdandcompany-context.md. If neither exists, say so and point to the build skills. If both exist, refresh them one at a time (ask which first).
- Read and date-check. Read the file. Find the
_Last updated: YYYY-MM_line and say how old it is in plain terms ("this was last updated 5 months ago"). Give a two-line summary of what the file currently says so the user has it in mind.
- Go section by section — probe, don't just ask "what changed?" For each section, read it back in one line and check:
- Is this still true? Roles, offers, clients and positioning drift over time.
- Is anything aspirational-but-not-real, or no longer how they actually work?
- Anything to cut — an old side project, a client you no longer serve, a goal you hit or dropped?
Ask them to confirm, correct, or cut. Keep it a quick pass, not a full re-interview.
- Check for gaps against the template. Compare the file's sections to the reference list below. If a useful section is missing, offer to add it — don't force it.
- Rewrite and report. Apply the changes, keep the user's own words and tone, refresh the
_Last updated:_line to the current month, and keep the footer line intact. Then show a short summary of what changed, e.g. "updated: offer, clients · added: goals · removed: old side project."
Section reference
Refresh against the same structure the build skills use (match whatever language the file is in):
- personal-context — Identity · Background · Day to day · How I work · Communication & voice · Goals · How AI should help me · Anything else
- company-context — The company · Offer · Customers · Personas · Positioning & messaging · Voice · Team · Client-facing know-how · Anything else
Polish files use the translated headings (e.g. Tożsamość, Oferta) — keep the file's existing headings, don't switch languages.
Notes
- Work in the file's language.
- Never overwrite without confirmation — show what you'll change first, then write.
- Respect privacy — don't add sensitive data the user didn't offer.
- If the directory is a shared or git-tracked repo, remind them not to commit personal details by accident.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nocodework
- Source: nocodework/ai-context-kit
- License: MIT
- Homepage: https://nocodework.io
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.