Install
$ agentstack add skill-webioinfo01-aweskill-aweskill ✓ 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
Aweskill
Use aweskill CLI directly. Do not add wrapper scripts unless the CLI is missing a needed capability.
Intent Router
Match the user's intent to a task domain, then follow the workflow below.
| User intent | Domain | First command | |---|---|---| | "Find a skill for X", "search skills", "install from GitHub" | Source Lifecycle | aweskill find | | "Scan and import local skills", "what's in the store", "remove a skill from the store" | Store Work | aweskill store list --verbose | | "Create a bundle", "add skills to a bundle", "show bundle contents" | Bundle Work | aweskill bundle list --verbose | | "Give Codex skill X", "project a bundle to Cursor", "remove a projection" | Projection Work | aweskill agent list --verbose | | "Update a skill", "refresh skills", "更新技能" | Source Lifecycle | aweskill update --check | | "Update aweskill itself", "upgrade the CLI" | Self-Update | aweskill self-update --check | | "Something is broken", "skill not showing up", "duplicate skills" | Escalate | Hand off to $aweskill-doctor |
First-Time Setup
If aweskill is not installed or the store is not initialized, run the full bootstrap:
- Install the CLI:
npm install -g aweskill - Initialize the central store:
aweskill store init - Confirm the store location:
aweskill store where --verbose - Project built-in skills to the current agent:
aweskill agent add skill aweskill,aweskill-doctor --global --agent - Verify:
aweskill agent list --global --agent— both skills should show aslinked - Tell the user to invoke skills (
/or$, depending on the agent) and check if the new skills appear. If they do, the skills are ready to use. If not, ask the user to restart the agent.
If aweskill is already installed but the store is not initialized, start from step 2. If the store is initialized but skills are not projected, start from step 4.
Core Rules
Inspect before mutating:
- Run a read-only inspection command first.
- Confirm scope:
--globalor--project [dir]. - Confirm target agent with
--agentwhen the command touches projections. - Run the mutating command only after the current state is clear.
- Re-run inspection after mutation to verify the result.
For complex changes, also decide:
- Whether the source of truth should remain the central store, a bundle, or an existing agent root.
- Whether the task is single-scope or truly needs both
--globaland--project. - Whether the task is single-agent or should be applied agent-by-agent with explicit
--agent.
Workflows
Source Lifecycle
Use when the task is about searching upstream sources, installing tracked skills, or refreshing them.
# Search upstream providers
aweskill find
aweskill find --local # search local store only
aweskill find -p # limit to one provider (skills-sh, sciskill, local)
aweskill find -l # limit results (default 10)
aweskill find --domain # sciskill domain filter
aweskill find --stage # sciskill stage filter
# Install from GitHub, local path, or sciskill ID
aweskill install
aweskill install --skill # install one skill from a multi-skill source
aweskill install --list # list downloadable skills without installing
aweskill install --all # install all skills from the source
aweskill install --ref # git branch or tag (GitHub sources only)
aweskill install --as # install under a different name
aweskill install --override # overwrite existing skills
# Check tracked skills for updates
aweskill update --check
# Refresh tracked skills
aweskill update [skill...]
aweskill update --dry-run # show actions without modifying
aweskill update --source # only update skills from a source
aweskill update --override # discard local changes and overwrite
Decision order:
findwhen the source is not yet known.installwhen the source is known and the skill should enter the central store.update --checkwhen the user wants visibility before change.updatewhen the skill is already tracked and should be refreshed.
Store Work
Use when the task is about existing local skills that need to be brought into or managed inside the central store.
# See what's in the central store
aweskill store list --verbose
# Inspect one managed skill
aweskill store show
# Scan agent skill directories (dry-run: only discover)
aweskill store scan
aweskill store scan --verbose # show skill names and paths
aweskill store scan --scope project # scan project scope only
aweskill store scan --agent claude # scan specific agent only
# Scan and import discovered skills
aweskill store scan --import # import all discovered skills (replaces with symlinks)
aweskill store scan --import --override # overwrite existing files
aweskill store scan --import --keep-source # keep originals instead of replacing with symlinks
aweskill store scan --import --verbose # import with detailed output
# Remove a skill from the central store
aweskill store remove
# Backup and restore
aweskill store backup [archive]
aweskill store backup --skills-only # exclude bundles
aweskill store restore
aweskill store restore --override # replace existing skills
Self-Update
Use when the task is about updating the aweskill CLI tool itself, or when the installed CLI behaves differently from the repo code.
# Check current vs latest npm version
aweskill self-update --check
# Update from npm registry (stable)
aweskill self-update
# Check latest dev branch commit
aweskill self-update --dev --check
# Build and install from GitHub dev branch
aweskill self-update --dev
If the user reports that the installed aweskill doesn't match what they expect from the repository:
- Check which binary is active:
which aweskill - Check installed version vs npm latest:
aweskill self-update --check - If dev branch is needed:
aweskill self-update --dev --check && aweskill self-update --dev - If the issue persists, inspect the installed
dist/index.jsor global package target to confirm which code is actually running.
Bundle Work
Use when the task is about organizing reusable skill sets before projecting them into agents.
# See bundles
aweskill bundle list --verbose
# Create a bundle
aweskill bundle create
# Add or remove skills
aweskill bundle add
aweskill bundle remove
# Inspect a bundle
aweskill bundle show
# Delete a bundle
aweskill bundle delete
# Import a built-in bundle template
aweskill bundle template import
Projection Work
Use when the task is about applying central-store skills or bundles into agent roots.
# See supported agents
aweskill agent supported
# Inspect projected agent state
aweskill agent list [--global|--project [dir]] [--agent ] --verbose
# Project a skill or bundle
aweskill agent add skill --global --agent
aweskill agent add bundle --project [dir] --agent
aweskill agent add skill --global --agent --force # replace duplicates/foreign targets
# Remove a managed projection
aweskill agent remove skill --global --agent
aweskill agent remove skill --global --agent --force # also remove duplicates/foreign targets
# Recover one agent root into copied directories
aweskill agent recover --global --agent
For scope-sensitive or multi-agent projection:
- Decide whether target should be
--globalor--project [dir]. - Run
aweskill agent supportedif agent IDs are uncertain. - Use
aweskill agent listbefore projecting. - Apply changes one scope at a time unless the user explicitly wants multi-scope rollout.
- Re-run
aweskill agent list --verboseto verify the result.
Escalation to Doctor
Hand off to $aweskill-doctor when the symptom matches one of these categories:
| Symptom | Doctor workflow | |---|---| | agent list shows broken | Projection is Broken | | agent list shows duplicate or matched | Duplicate Skills Exist | | agent list shows suspicious or new | Store Has Suspicious Files | | store list or doctor clean reports suspicious entries | Store Has Suspicious Files | | doctor fix-skills reports malformed frontmatter | SKILL.md Frontmatter is Malformed | | User says "skill not showing up" | Agent Cannot See a Skill | | User asks to "repair", "clean", "deduplicate", or "sync" | Run inspection first, then follow the matching symptom workflow |
Do NOT escalate for CLI version mismatches or self-update issues — handle those in the Self-Update workflow above.
References
references/common-flows.md— common day-to-day command sequencesreferences/command-map.md— fast route from user intent to CLI command
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Webioinfo01
- Source: Webioinfo01/aweskill
- License: MPL-2.0
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.