cc-skill-strategic-compact
Helps your agent save important progress in long tasks. This ensures crucial decisions and information aren't lost as the conversation continues.
What it does
This tool helps summarize the progress of a long and complex task. It saves important information about what has been done, what still needs to be done, and any key rules or decisions, so you can pick up where you left off without losing context.
When to use it
- ✓When a major milestone of a project is completed.
- ✓If the conversation with the AI is becoming too long and repetitive.
- ✓Before starting a new important phase in a task.
Example of what to ask your AI
“Save the progress of my current task. I want to be able to continue later.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool identifies key points from the conversation, such as the main objective, established rules, what has been completed, and what is missing. It organizes this information into a clear summary for later use.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill cc-skill-strategic-compactOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/cc-skill-strategic-compact/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Strategic Context Checkpoints
Condense context after a verified phase, with enough durable information to resume the same task. A tool-call count is only a reminder; it cannot measure context quality or decide when compaction is safe.
When to Use
Use when exploration has finished, a tested milestone has landed, or a long conversation contains repeated or obsolete reasoning. Do not compact in the middle of an unresolved tool call, an unrecorded approval decision, or a failure whose exact evidence has not been captured.
Inputs and prerequisites
- The user's current objective, accepted constraints and definition of done.
- The current branch and source revision, local changes, relevant artifact paths and actual check results.
- Running processes, pending tool calls, approvals or external blockers.
- A host-supported context-compaction mechanism. This skill does not assume
/compactexists in every client or manipulate internal context files.
Procedure
- Choose a phase boundary: discovery to implementation, implementation to verification, or one completed batch to the next. Preserve an unresolved failure's reproduction first.
- Reconcile task state with the filesystem and Git. Distinguish completed, uncommitted, planned and failed work.
- Produce the checkpoint below. Include exact commands, result summaries and paths needed to resume; omit copied logs and discarded hypotheses that no longer matter.
- Check that the next action is executable and that a new context would not repeat a merge, send a message twice, lose a constraint or overwrite unrelated work.
- Save only in an already authorized project artifact, or return the checkpoint in the conversation. Do not rewrite global memory or host configuration automatically.
- Use the client's supported compaction command if requested and available. On resumption, read the checkpoint and verify mutable state before continuing.
Checkpoint template
Objective and done condition:
User constraints and authorization boundaries:
Source revision, branch and local changes:
Completed outcomes with verification:
Outstanding work and known failures:
Running process/tool identifiers:
Artifacts and exact paths needed next:
Next action, expected result and fallback:
Worked example
For a search feature whose source PR merged while canonical synchronization is pending, preserve the source merge SHA, canonical PR number and expected generated files. Record tests as passed only for the revision actually tested. The next action is to verify the canonical PR and updated main; it is not to merge the source PR again. If a browser check still needs an unlocked desktop, keep that condition visible while continuing independent code review.
Expected outcome: the next context resumes outstanding verification, preserves unrelated local edits and does not claim publication from a source merge.
Optional stateless reminder
bash skills/cc-skill-strategic-compact/suggest-compact.sh 50
The helper accepts an observed tool-call count and optional threshold (default 50), and prints a reminder at the threshold and every 25 calls after it. COMPACT_TOOL_COUNT and COMPACT_THRESHOLD can be supplied by an explicit caller adapter. It stores no counter, estimates no token usage and never performs compaction. With no count it exits quietly.
Earlier versions incremented a shared user-state counter across unrelated sessions. That counter is no longer read or written; existing custom wrappers must pass a session count explicitly. Existing state files are left untouched. This skill does not install or edit a hook.
Limitations
- A checkpoint preserves recorded evidence, not all conversation detail. Keep primary artifacts when exact bytes matter.
- Counts are caller-provided, bounded non-negative decimal integers; reminders are not a context-capacity measurement.
- Branches, processes and remote checks can change after a checkpoint. Revalidate them instead of treating a summary as current truth.
- Client context management differs. Do not simulate compaction by deleting chat databases, logs, caches or project files.
FAQ
What happens to the conversation details?
The tool focuses on essential details for resuming the task, like important decisions and outcomes. Less critical or already resolved details might be omitted to keep the summary concise.
Can I trust that everything will be saved?
The tool saves recorded information and evidence. However, external changes or changes in the working environment after saving might need to be re-verified.
Does this delete anything?
No, this tool does not delete project files, logs, or configurations. It only creates an organized summary of important information.
Details
Original description by the author
Prepare a verified checkpoint before condensing an agent conversation at a phase boundary. Use during long tasks when context is repetitive; preserves constraints, evidence, decisions and the next action.
Popularity
- GitHub stars
- 48k
- Ranking position
- #2504
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
benchmark
Helps your agent measure code speed and performance. It's useful for ensuring things are fast and finding slowness issues.
affaan-m/ECC
content-hash-cache-pattern
Lets your agent use content hashes to cache file processing results. This avoids repeated processing and auto-invalidates the cache when content changes. Useful for speeding up slow tasks.
affaan-m/ECC
parallel-execution-optimizer
Makes your agent speed up complex tasks by breaking them into smaller parts and running them in parallel. It ensures everything is verified at the end.
affaan-m/ECC