MVPavan/via / .claude/skills/execution
execution
VerifiedUse to execute tracked multi-step work, a standalone plan, or a roadmap phase. Clear bounded implementation can proceed directly under AGENTS.md.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.5 KB |
| agents/openai.yaml | config | 42 B |
| references/task-engine.md | markdown | 6.0 KB |
| references/workstream-mode.md | markdown | 2.1 KB |
| scripts/review-package.shexecutable | script | 2.7 KB |
| scripts/task-brief.shexecutable | script | 1.6 KB |
scripts/task-brief.sh
View on GitHub#!/usr/bin/env bash
# Extract one task from an implementation plan into a brief file the
# implementer reads in one call, so the task text never passes through the
# coordinator's context. The brief = the plan preamble (everything before the
# first task heading — Origin, Goal, Out of scope, Constraints, which every
# task implicitly includes per plan-format.md) plus the requested task's
# section. Matches plan-format.md headings: "### Task N: <name>" at any
# heading depth; a task section ends at the next heading of any kind
# (plan-format tasks contain no sub-headings).
#
# Usage: task-brief.sh PLAN_FILE TASK_NUMBER WORKSPACE_DIR
# Writes: WORKSPACE_DIR/task-<N>-brief.md
set -euo pipefail
if [ $# -ne 3 ]; then
echo "usage: task-brief.sh PLAN_FILE TASK_NUMBER WORKSPACE_DIR" >&2
exit 2
fi
plan=$1
n=$2
dir=$3
[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }
case "$n" in
''|*[!0-9]*|0*) echo "TASK_NUMBER must be a positive integer: '$n'" >&2; exit 2 ;;
esac
mkdir -p "$dir"
out="$dir/task-${n}-brief.md"
awk -v n="$n" '
/^(```|~~~)/ { infence = !infence; if (intask || !seentask) print; next }
infence { if (intask || !seentask) print; next }
/^#+[ \t]/ {
if ($0 ~ /^#+[ \t]+Task[ \t]+[0-9]+:/) {
seentask = 1
intask = ($0 ~ ("^#+[ \t]+Task[ \t]+" n ":"))
} else {
intask = 0
}
}
{ if (intask || !seentask) print }
' "$plan" > "$out"
if ! grep -Eq "^#+[[:space:]]+Task[[:space:]]+${n}:" "$out"; then
rm -f "$out"
echo "task ${n} not found in ${plan} (no heading matching 'Task ${n}:')" >&2
exit 3
fi
echo "wrote ${out}: $(wc -l < "$out" | tr -d ' ') lines"
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: 466k | Updated | Claude CodeCodex | Verified | 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: 466k | 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: 319k | 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: 319k | Updated | Claude CodeCodex | Verified | Install |