j-mauro-r/SAT-Dengue-V2 / .agents/skills/deepworkplan
deepworkplan
VerifiedDeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, upgrade, and repo-onboarding sub-skills based on intent. Use when the developer wants to plan, execute, manage, or verify structured multi-task work, or make a repository AI-agent-ready.
addons/machine-installs.md
View on GitHub# Addons — machine-level installs and upgrades (verified)
Read from `../onboard/all-addons.md` §4, or from an addon's own install step.
These commands change the developer's machine, not the repository: show
them, and run them only when the developer accepts, in an interactive
session. Each tag below is the pack's pin for that addon (its `addon.json`
`product.tag`, printed by `../shared/addon_sync.py plan`).
**Kits.** Both installers upgrade in place, so install and upgrade are the
same sequence at the pin, with three gates before the installer runs: the
tag checked, the downloaded `SHA256SUMS` checked against the digest pinned
here, and the tree checked against `SHA256SUMS` with at least one file
actually verified (`--ignore-missing` alone would pass with none).
coding-agents-kit (`agentkit`):
```bash
git clone --branch v1.0.1 --depth 1 https://github.com/DailybotHQ/coding-agents-kit cak
git -C cak describe --tags --exact-match # must print v1.0.1
curl -fsSL https://github.com/DailybotHQ/coding-agents-kit/releases/download/v1.0.1/SHA256SUMS -o cak.SHA256SUMS
echo "de17573e57de9eeb44914189cbc1fd0b1322797cc398c710dadfecc08758db6f cak.SHA256SUMS" | shasum -a 256 -c # the pinned digest
(cd cak && shasum -a 256 -c --ignore-missing ../cak.SHA256SUMS) # must exit 0
(cd cak && shasum -a 256 -c --ignore-missing ../cak.SHA256SUMS | grep -c ': OK$') # must print a number above 0
./cak/install.sh
```
devcontainer-kit (`devcontainer`):
```bash
git clone --branch v1.0.1 --depth 1 https://github.com/DailybotHQ/devcontainer-kit dck
git -C dck describe --tags --exact-match # must print v1.0.1
curl -fsSL https://github.com/DailybotHQ/devcontainer-kit/releases/download/v1.0.1/SHA256SUMS -o dck.SHA256SUMS
echo "90d8ff62281c3671b1f800dd8de06ac14404069e032876648500b066419393a2 dck.SHA256SUMS" | shasum -a 256 -c # the pinned digest
(cd dck && shasum -a 256 -c --ignore-missing ../dck.SHA256SUMS) # must exit 0
(cd dck && shasum -a 256 -c --ignore-missing ../dck.SHA256SUMS | grep -c ': OK$') # must print a number above 0
./dck/install.sh
```
Re-detect afterwards (`ak doctor --json`, `dck doctor --json`); the
interface must match the descriptor. dck additionally installs the
repository-local `dck-dockerfile` skill at the same tag
(`devcontainer/SKILL.md`, Step 2).
**herdr-peers** (host): the pinned skill installs in
`herdr/install.md`; `dck setup` also installs a verified
herdr-peers on the host. Verify with `herdr-peers --version`
(`(protocol 1)`).
**DeepWorkPlan Vim:** the product's own checksum-verified installer under
its consent gate (`vim/SKILL.md`); an existing Neovim config is
never overwritten without explicit consent.
A failed tag check or a checksum mismatch stops the install: report it,
never run the installer anyway. Never pipe a download into a shell, never
install a coding-agent CLI the developer did not choose, and never set an
autonomy flag.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |