agentleFS
SkillMedevSkillMedev/social-media-studio/skills/hashtag-strategist/SKILL.md

hashtag-strategist

Skill1 starsChanged 42 days agoMITView on GitHub

Builds a tiered hashtag and keyword set sized to the account's actual reach - mixing broad, niche, and branded tags per platform limits and screening out banned, spammy, or shadow-flagged tags. Use when someone asks "what hashtags should I use", "build me a hashtag set for this post", "audit my tag block", or is creating reusable tag sets per content pillar on Instagram, TikTok, LinkedIn, X, or YouTube. Do NOT use for writing the caption itself - use social-caption-writer instead. Do NOT use for clustering SEO search keywords by topic or intent - use keyword-cluster-builder instead.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every set mixes three tiers.

    line 26
  2. Distinctive:

    Follow-for-follow and engagement-pod tags - they attract bots and can flag the account itself.

    line 52
  3. Distinctive:

    Do NOT dump the platform maximum (e.g.

    line 88
  4. Distinctive:

    Do NOT recommend broad 1M+ tags as the core for a small account - one or two aspirational bets, never the workhorse.

    line 89
  5. Distinctive:

    Do NOT include follow-for-follow, engagement-pod, or unvetted generic-noise tags.

    line 90
  6. Distinctive:

    Do NOT skip the tag-feed check.

    line 91
  7. Distinctive:

    Do NOT promise tags will rescue a post - if the real problem is content quality or posting consistency, say so plainly.

    line 92
  8. Distinctive:

    Do NOT produce a topic/intent-clustered SEO keyword map.

    line 93

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Hashtag Strategist

Produce a tiered, platform-sized hashtag set plus in-caption keywords matched to the account's actual reach, not to tag volume. The costly mistake this skill prevents: small accounts stuffing broad million-post tags where they are buried in seconds, or dumping the platform maximum and reading as spam. Tag competitiveness must track account size the way keyword difficulty tracks domain authority.

Operating procedure

Step 1: Gather inputs

Collect before building anything; where a number is unknown, use the stated default and label it a guess.

  1. Platform (Instagram, TikTok, LinkedIn, X, or YouTube) - this sets the count ceiling.
  2. Account scale: follower count and typical views per post (default assumption if unknown: small, under 10k followers - size down, not up).
  3. The specific post or the content pillars the sets will serve.
  4. Brand tag and any community tags already in use.
  5. Who the target viewer is and what they would literally type into search.

Step 2: Build the three tiers in ratio

Every set mixes three tiers. For a standard 6-tag Instagram set, the working ratio is roughly 1-2 broad : 3-4 niche : 1-2 branded - the niche tier is always the majority.

  • Broad / high-volume (1M+ posts): one or two only. Aspirational reach, never the workhorse; a small account ranks on these for seconds.
  • Niche / mid (10k-500k posts): the core of the set - specific enough that the post can rank and stay visible for hours or days.
  • Branded / community (the brand tag plus 1-2 small community tags): always include, to build a searchable archive and community surface.

The smaller the account, the harder the set skews niche and small: an account under 10k followers should pull its niche tier from the 10k-100k end of the range.

Step 3: Size the set to the platform

  • Instagram: 3-8 well-chosen tags. The 30-tag maximum is a ceiling, not a target.
  • TikTok: 3-5 - one broad discovery tag plus specific topical ones.
  • LinkedIn: 1-3 that read naturally inline.
  • X: 1-2 maximum.
  • YouTube: a few tags, but lean on keyword-rich titles and descriptions - tags are the minor lever there.

Step 4: Add first-class keywords

Recommend the literal search phrases a target viewer would type, woven naturally into the caption, on-screen text, or title/description. On search-surfaced platforms (TikTok, YouTube, increasingly Instagram) this is often higher-leverage than the tag list. Keep these as in-context phrases for THIS post; a standalone topic-clustered keyword map is keyword-cluster-builder's job.

Step 5: Vet every tag

Reject, with no exceptions:

  • Banned, broken, or shadow-flagged tags - they silently suppress the whole post. Check the tag's feed: if a populated tag shows no recent posts or a warning, it is flagged.
  • Tags hijacked by unrelated or spammy content (open the tag feed and look at the top 9).
  • Follow-for-follow and engagement-pod tags - they attract bots and can flag the account itself.

Step 6: Deliver rotating sets

Provide 2-3 interchangeable sets tied to content pillars so the account never posts an identical block, which platforms can read as automated.

Worked example: one post

Post: a 60-second Instagram Reel, "3 mobility drills for desk workers," from a physiotherapist account with 4,200 followers.

SET A (6 tags - 1 broad / 4 niche / 1 branded)
  Broad:   #mobility                    (2M+ posts - the one reach bet)
  Niche:   #deskstretches               (~40k)
           #mobilitydrills              (~180k)
           #deskworkerhealth            (~15k)
           #physioexercises             (~90k)
  Branded: #[FILL: brandname]moves

IN-CAPTION KEYWORDS (woven into the first two lines, not a list)
  "mobility drills for desk workers", "fix desk posture",
  "stretches you can do at your desk"

VETTED OUT
  #fitfam (pod-adjacent, bot-heavy), #followforfollow (account-flag risk),
  #stretching variant that surfaced unrelated spam in its top posts

Bad set for this account: #fitness #gym #health #workout #motivation #fitfam - six broad or polluted tags, zero chance of ranking, no archive value.

Deliverable

Produce a tag strategy containing: 2-3 rotating sets (each with tiers labeled and approximate post volumes), the in-caption keyword phrases for the post at hand, the vetted-out list with reasons, and the platform count rule applied.

Do NOT

  • Do NOT dump the platform maximum (e.g. 30 Instagram tags); relevance beats quantity.
  • Do NOT recommend broad 1M+ tags as the core for a small account - one or two aspirational bets, never the workhorse.
  • Do NOT include follow-for-follow, engagement-pod, or unvetted generic-noise tags; they attract bots and risk flagging the account.
  • Do NOT skip the tag-feed check; one shadow-flagged tag can suppress the entire post silently.
  • Do NOT promise tags will rescue a post - if the real problem is content quality or posting consistency, say so plainly.
  • Do NOT produce a topic/intent-clustered SEO keyword map; that is keyword-cluster-builder's job.

Quality bar

A finished set ships only when: every tier is present and the niche tier is the majority; the count respects the platform ceiling; every tag has an approximate post volume attached and passed the vet; at least one in-caption keyword phrase set is delivered alongside the tags; and there are 2-3 rotating sets mapped to pillars, not one frozen block.

Adjacent jobs

For writing the caption the tags attach to, route to social-caption-writer. For a standalone SEO keyword architecture, route to keyword-cluster-builder.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.