Ijfw Compute
Compute over read. Run sandboxed scripts to process data instead of dumping it into context. Trigger: 'compute', 'process this data', 'analyze logs', or PreToolUse nudge.
Install
npx skills add FerroxLabs/wayland-core --skill ijfw-computegit clone --depth 1 https://github.com/FerroxLabs/wayland-core.git /tmp/wayland-core
mkdir -p ~/.claude/skills
cp -r /tmp/wayland-core/crates/wayland-ijfw/snapshots/ijfw-source/claude/skills/ijfw-compute ~/.claude/skills/ijfw-computePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
Compute over read. When data is large or repetitive, run a sandboxed script
and surface only the result. The four trees below decide which lever to pull.
## Compute tree -- run a sandboxed script
Use when the input is bigger than the answer: log files, CSV/JSON dumps,
file-tree walks, repeated string transforms, aggregate stats, deduping.
Call `ijfw_run compute:python "<script>"` for pandas / numpy / stdlib parsing.
Call `ijfw_run compute:js "<script>"` for JSON shape-checks, regex sweeps,
quick numeric work. Sandbox is allowlist filesystem (cwd + project root) +
best-effort OS-level network deny; opt-in with `IJFW_COMPUTE_NET=1` if the
script needs egress. Default timeout 30s, hard cap 300s via
`IJFW_COMPUTE_TIMEOUT_MS`. Output cap 100MB; overflow lands in the on-disk log.
Example: a 40MB nginx log. Instead of reading 200k lines into context, run
`ijfw_run compute:python "import collections,sys;c=collections.Counter();[c.update([l.split()[8]]) for l in open('access.log')];print(c.most_common(10))"`
and surface the top-10 status-code summary.
## Read tree -- skip compute, just read
Use when the file is small (<2k lines), the task is a code edit or config
tweak, or the agent needs to reason about structure rather than aggregate
content. Direct Read is cheaper than spinning a subprocess; compute has
fixed startup overhead.
Example: editing a single function in `mcp-server/src/server.js`. Read the
file, edit it, move on. No compute call needed.Details
- Skill name
ijfw-compute- Repository
- FerroxLabs/wayland-core
- Path
crates/wayland-ijfw/snapshots/ijfw-source/claude/skills/ijfw-compute/SKILL.md- License
- Apache-2.0
- Repo updated
- 3 November 2026
FAQ
What does the Ijfw Compute skill do?
Compute over read. Run sandboxed scripts to process data instead of dumping it into context. Trigger: 'compute', 'process this data', 'analyze logs', or PreToolUse nudge.
How do I install the Ijfw Compute skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add FerroxLabs/wayland-core --skill ijfw-compute. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Ijfw Compute popular?
It lives in FerroxLabs/wayland-core, which has 43 GitHub stars and 17 forks.
Related skills
Ijfw Agents Md
43FerroxLabs/wayland-core
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.
Ijfw Auto Memorize
43FerroxLabs/wayland-core
Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires consent on first run.
Ijfw Commit
43FerroxLabs/wayland-core
Terse conventional commits. Trigger: commit, git commit, /ijfw-commit
Ijfw Critique
43FerroxLabs/wayland-core
Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.
Overview
49lis186/SourceAtlas
Get project overview - scan <5% of files to achieve 70-80% understanding
Ijfw Handoff
43FerroxLabs/wayland-core
Session handoff generation and loading. Trigger: session end, context full, /handoff
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.